Automated Dental Restoration

Abstract

A computer-implemented method and system for automating virtual dental restoration design includes receiving a 3D virtual dental model of at least a portion of a patient's dentition, the 3D virtual dental model comprising at least one virtual abutment-prepared tooth, the virtual abutment-prepared tooth comprising a digital representation of a physical abutment-prepared tooth prepared by a dentist; performing automated virtual restoration design using the 3D virtual dental model; virtually displaying to the dentist any issues with the one or more physical abutment-prepared teeth detected during the automated virtual restoration design; and virtually displaying the generated virtual restoration to the dentist for one or more adjustments if no issues with the physical abutment teeth are detected during the automated virtual restoration design.

Description

[Technical Field]

[0001] This application claims priority to and benefit of pending U.S. Provisional Patent Application No. 63 / 369,151, filed July 22, 2022, entitled "Integrated Dental Restoration Design Process and System," pending U.S. Provisional Patent Application No. 63 / 380,374, filed October 20, 2022, entitled "Dental Restoration Automation," and U.S. Patent Application No. 18 / 353,947, filed July 18, 2023, entitled "Dental Restoration Automation," all of which are incorporated herein by reference in their entireties. [Background technology]

[0002] Traditional dental care typically involves a dentist seeing a patient in their dental office and performing an examination of the patient's dentition. The examination / treatment at the dental office is sometimes referred to as "chairside" because the patient is seated in a dental chair. During a typical chairside visit, the patient may require a dental restoration for one or more teeth. The dentist typically anesthetizes the patient or a portion of the patient's dentition and physically prepares the one or more teeth to receive the dental restoration. During this preparation chairside visit, the dentist may modify the one or more existing teeth in a manner that allows the restoration to fit properly on the particular prepared tooth or teeth. Examples of restorations may include, without limitation, crowns, bridges, inlays, etc.

[0003] In some cases, once the physical tooth or teeth have been prepared, the dentist may directly scan the patient's dentition, including the physical abutment preparations, to generate a 3D virtual model of the patient's dentition, including virtual abutment preparations that represent the physically prepared teeth. In some cases, this scanning operation may be performed using an optical scanner, such as an intraoral scanner, to generate a 3D virtual model of at least a portion of the patient's dentition, including the abutment preparations.

[0004] In some cases, the dentist may have the patient create an impression by having the patient bite down on impression material placed in an impression tray to create a physical impression, which can be mailed to a dental laboratory where a plaster mold of the patient's dentition is made from the physical impression.

[0005] In some cases, a 3D physical plaster model of the patient's dentition is fabricated from the physical impression and then optically scanned in a dental laboratory. Alternatively, the physical impression itself can be scanned using an optical scanner, such as an intraoral scanner or a computed tomography ("CT") scanner, to generate a 3D virtual model of the patient's dentition, including the abutment preparations, in the dental laboratory.

[0006] In recent years, CAD / CAM dentistry (computer-aided design and computer-aided manufacturing in dentistry) has offered a wide range of dental restorations, including crowns, veneers, inlays, onlays, fixed bridges, dental implant restorations, and orthodontic appliances. In a typical CAD / CAM-based dental procedure, a treating dentist may prepare a tooth to be restored as either a crown, inlay, onlay, or veneer. The prepared tooth and its surroundings are then scanned with a three-dimensional (3D) imaging camera and uploaded to a computer for design. Alternatively, the dentist may take an impression of the tooth to be restored, which may be scanned directly or formed into a model that is scanned and uploaded to a computer for design.

[0007] Current dental CAD systems are often laborious and time-consuming, resulting in inconsistent designs and potential errors. In some cases, problems with the physical abutment preparation tooth can prevent or delay the design of a restoration for the abutment preparation tooth. These problems can include, for example, but are not limited to, one or more undercut areas, margin line problems, one or more gap problem areas, and / or restoration insertion problems in the physical abutment preparation tooth. These problems can recur over time if not addressed. It is desirable for dentists to detect and address these problems so that errors can be minimized. Summary of the Invention

[0008] A computer-implemented method for automating virtual dental restoration design may include receiving a 3D virtual dental model of at least a portion of a patient's dentition, the 3D virtual dental model comprising at least one virtual abutment-prepared tooth, the virtual abutment-prepared tooth comprising a digital representation of a physical abutment-prepared tooth prepared by a dentist; performing automated virtual restoration design using the 3D virtual dental model; virtually displaying to the dentist any issues with the one or more physical abutment-prepared teeth detected during the performing of the automated virtual restoration design; and virtually displaying the generated virtual restoration to the dentist for one or more adjustments if no issues with the physical abutment-prepared teeth are detected during the performing of the automated virtual restoration design.

[0009] A non-transitory computer-readable medium storing executable computer program instructions for providing automated virtual dental restoration design, the computer program instructions may include instructions for receiving a 3D virtual dental model of at least a portion of a patient's dentition, the 3D virtual dental model comprising at least one virtual abutment-prepared tooth, the virtual abutment-prepared tooth comprising a digital representation of a physical abutment-prepared tooth prepared by a dentist; performing automated virtual restoration design using the 3D virtual dental model; virtually displaying to the dentist any issues with the one or more physical abutment-prepared teeth detected during the performing of the automated virtual restoration design; and virtually displaying the generated virtual restoration to the dentist for one or more adjustments if no issues with the physical abutment-prepared teeth are detected during the performing of the automated virtual restoration design.

[0010] A system for automating virtual dental restoration design may include a processor; and a non-transitory computer-readable storage medium comprising instructions executable by the processor to perform the steps of receiving a 3D virtual dental model of at least a portion of a patient's dentition, the 3D virtual dental model comprising at least one virtual abutment-prepared tooth, the virtual abutment-prepared tooth comprising a digital representation of a physical abutment-prepared tooth prepared by a dentist; performing automated virtual restoration design using the 3D virtual dental model; virtually displaying to the dentist any issues with the one or more physical abutment-prepared teeth detected during the performance of the automated virtual restoration design; and virtually displaying the generated virtual restoration to the dentist for one or more adjustments if no issues with the physical abutment-prepared teeth are detected during the performance of the automated virtual restoration design. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 illustrates a diagram of a cloud computing environment for a dental restoration automation system in some embodiments. [Figure 2] FIG. 2 shows a diagram of dental restoration automation in some embodiments. [Figure 3] FIG. 3 shows a diagram of dental restoration automation in some embodiments. [Figure 4] FIG. 4 shows a diagram of one or more steps that may be used in the automated design of a virtual dental modification in some embodiments. [Figure 5(a)] FIG. 5(a) illustrates decimation performed on a 3D virtual model mesh in some embodiments. [Figure 5(b)] FIG. 5(b) illustrates the decimation performed on the 3D virtual model mesh in some embodiments. [Figure 5(c)] FIG. 5(c) illustrates the decimation performed on the 3D virtual model mesh in some embodiments. [Figure 6] FIG. 6, for example, illustrates a diagram of a convolutional neural network in some embodiments. [Figure 7] FIG. 7, for example, illustrates a top perspective view of an example 2D depth map of a digital model in some embodiments. [Figure 8] FIG. 8 shows a top perspective view of the 3D virtual model in the occlusal direction, the virtual abutment forming mold area and the buccal direction. [Figure 9(a)] FIG. 9(a), for example, shows a diagram of a hierarchical neural network in some embodiments. [Figure 9(b)] FIG. 9(b), for example, shows a diagram of a hierarchical neural network in some embodiments. [Figure 10] FIG. 10, for example, illustrates a diagram of a deep neural network in some embodiments. [Figure 11] FIG. 11, for example, shows a diagram of a computer-implemented method for automatic margin line proposal in some embodiments. [Figure 12] FIG. 12, for example, illustrates a perspective view of an example 3D digital model showing proposed margin lines from a base margin line in some embodiments. [Figure 13(a)]FIG. 13(a), for example, shows a perspective view of a 3D digital model with an abutment preparation and proposed margin line in some embodiments. [Figure 13(b)] FIG. 13(b), for example, shows a perspective view of a 3D digital model with a preparation tooth and proposed margin line in some embodiments. [Figure 14] FIG. 14 shows a 3D virtual model of a virtual abutment preparation with margin lines according to some embodiments. [Figure 15] FIG. 15 is a flowchart of a process for generating a 3D dental prosthesis model using a deep neural network according to some embodiments of the present disclosure. [Figure 16] FIG. 16 is a graphical representation of inputs and outputs of a deep neural network according to some embodiments of the present disclosure. [Figure 17(a)] FIG. 17(a) is a flow diagram of a method for training a deep neural network to generate a 3D dental prosthesis according to some embodiments of the present disclosure. [Figure 17(b)] FIG. 17(b) is a flow diagram of a method for training a deep neural network to generate a 3D dental prosthesis according to some embodiments of the present disclosure. [Figure 18] FIG. 18 shows a 3D virtual model of a virtual crown elevated onto a virtual abutment preparation along the insertion direction in some embodiments. [Figure 19] FIG. 19 shows a diagram of a computer-implemented method for automatic margin line proposal in some embodiments. [Figure 20] FIG. 20 shows a 3D virtual model of a virtual abutment preparation tooth with an open margin line according to some embodiments. [Figure 21] FIG. 21 shows a perspective view of a 3D virtual model with a virtual abutment preparation and marked open margins in some embodiments. [Figure 22] FIG. 22 shows a perspective view of a 3D virtual model with a virtual abutment preparation tooth and gap problems marked in some embodiments. [Figure 23(a)] FIG. 23(a) illustrates one or more adjustments made to a virtual restoration in a 3D virtual dental model. [Figure 23(b)] FIG. 23(b) illustrates one or more adjustments made to the virtual restoration in the 3D virtual dental model. [Figure 23(c)] FIG. 23(c) illustrates one or more adjustments made to the virtual restoration in the 3D virtual dental model. [Figure 23(d)] FIG. 23(d) illustrates one or more adjustments made to the virtual restoration in the 3D virtual dental model. [Figure 23(e)] FIG. 23(e) illustrates one or more adjustments made to the virtual restoration in the 3D virtual dental model. [Figure 23(f)] FIG. 23(f) illustrates one or more adjustments made to the virtual restoration in the 3D virtual dental model. [Figure 23(g)] FIG. 23(g) illustrates one or more adjustments made to the virtual restoration in the 3D virtual dental model. [Figure 24] FIG. 24 is a flow chart according to some embodiments. [Figure 25] FIG. 25 illustrates a computing system in some embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0012] For purposes of this description, certain aspects, advantages, and novel features of the disclosed embodiments are described herein. The disclosed methods, apparatus, and systems are not to be construed as limiting in any manner. The present disclosure is instead directed to all novel and non-obvious features and aspects of the various disclosed embodiments, alone or in various combinations and subcombinations with one another. The methods, apparatus, and systems are not limited to any particular aspect or feature or combination thereof, nor are the disclosed embodiments required to have any one or more particular advantages or problems solved.

[0013] Although some operations of the disclosed embodiments are described in a particular order for convenient presentation, it should be understood that this description encompasses reordering unless a particular order is required by specific language described below. For example, operations described sequentially may in some cases be reordered or performed simultaneously. Moreover, for simplicity, the accompanying drawings may not show various aspects by which the disclosed methods can be used in conjunction with other methods. Furthermore, the description may use terms such as "provide / provide / provide" or "achieve / achieve" to describe the disclosed methods. The actual operations corresponding to these terms may vary depending on the particular implementation and are readily discernible by those skilled in the art.

[0014] As used in this application and the claims, the singular forms "a," "an," and "the" include the plural forms unless the context clearly dictates otherwise. Furthermore, the term "comprises" means "comprising / consisting of." Also, the terms "coupled" and "associated" generally mean electrically, electromagnetically, and / or physically (e.g., mechanically or chemically) coupled or connected, and do not exclude the presence of intermediate elements between coupled or associated / associated items unless specifically stated to the contrary.

[0015] In some instances, values, procedures, or devices may be referred to as "lowest," "best," "smallest," etc. It should be understood that such descriptions indicate that a choice may be made between multiple alternatives, and that such a choice is not necessarily better, lesser, or preferred over other choices.

[0016] In the following description, certain terms may be used, such as "top," "bottom," "upper," "lower," "horizontal," "vertical," "left," and "right." These terms are used, where applicable, to provide some clarity to the description when dealing with relative relationships. However, these terms do not imply absolute relationships, positions, and / or orientations. For example, with respect to an object, a "top" surface can become a "bottom" surface simply by flipping the object over. It is still the same object.

[0017] All references to any other US applications and patents and any other publications are incorporated herein by reference in their entirety.

[0018] As used herein, the term "dental restoration" refers to any dental restoration (restoration), including, without limitation, a crown, bridge, denture, partial denture, implant, onlay, inlay, or veneer.

[0019] Some embodiments disclose a computer-implemented method for automating virtual dental restoration design. Some embodiments of the present disclosure may include a workflow capable of automatically executing one or more steps in an integrated virtual restoration design automation process and system. As part of the integrated workflow, some embodiments of the present disclosure may include a computer-implemented method and / or system for designing a dental restoration associated with a dental model of the dentition. The method and / or system, in some embodiments, may automatically provide a simplified, automated workflow for virtually designing a dental restoration and provide feedback to the dentist regarding the preparation of a dental preparation. In some embodiments, the integrated workflow, along with any corresponding computer-implemented method and / or system, may be implemented in a cloud computing environment. As is known in the art, a cloud computing environment may include, without limitation, one or more devices, such as, for example, one or more computing units, such as servers, networks, storage, and / or applications, that are internet-enabled and accessible to one or more authorized client devices. An example cloud computing environment may include, for example, Amazon Web Services. Other types of cloud computing environments may be used, including, but not limited to, private cloud computing environments available to a restricted set of clients, such as those within a company. In some embodiments, the system may be implemented in a cloud computing environment.

[0020] 1 illustrates an example of a cloud computing environment or system 102 for facilitating an integrated digital workflow for providing dental restoration design and / or fabrication, according to some embodiments. The cloud computing environment 102, in some embodiments, may include a dental restoration cloud server 104, automated design features 103, storage 107 (direct storage in a file system of a storage device, in a database, or any other storage known in the art), and other components generally known in the art for cloud computing. Each of the components in the cloud computing environment 102, in some embodiments, may be interconnected, for example, by the dental restoration cloud server 104, or directly with each other or through one or more other servers or computers in the cloud computing environment or system 102. One or more client devices 108, in some embodiments, may be connected to the dental restoration cloud server 104, either directly or through one or more networks 105. Each of the one or more client devices 108 may be connected to one or more scanners 109, known in the art, to, for example, scan a patient's dentition or dental impressions and provide a 3D virtual dental model of at least a portion of the patient's dentition. In some embodiments, one or more client devices 108 may be located, for example, at a dental office. The dental restoration cloud server 104 may be connected to one or more manufacturers 110 directly and / or via one or more networks 105. For simplicity and clarity of illustration, only one dental restoration cloud server 104, one automated design feature 103, one client device 108, one scanner 109, one third-party manufacturer 110, and one storage 107 is shown in FIG. 1 . An embodiment of the cloud computing environment 102 may have multiple dental restoration cloud servers 104, automated design features 103, client devices 108, scanners 109, manufacturers 110, and storage 107. Similarly, the features and configurations / connections configured by the various entities in FIG. 1 may vary in different embodiments. In some embodiments, the scanner 109 may be located at the dental office.In some embodiments, client device 108 may be located at a dental office. In some embodiments, one or more manufacturers 110 may include, for example, one or more dental laboratories. One or more of the features shown in FIG. 1 may be implemented in and / or within one or more computing environments.

[0021] As part of dental restoration automation, the dental restoration cloud server 104, in some embodiments, may receive dental restoration cases from client devices 108 operated by clients, manage dental restoration cases among different clients, and provide finished dental restoration designs and / or milled dental modifications to the clients. In some embodiments, a dental restoration case may include a design-only case that requires the dental restoration cloud server 104 to provide a virtual design of a dental restoration. In some embodiments, a dental restoration case may require the dental restoration cloud server 104 to not only provide a design but also fabricate the dental restoration. In some embodiments, a dental restoration case may only require fabrication.

[0022] Some embodiments of the computer-implemented method for automating virtual dental restoration design may include receiving a 3D virtual dental model of at least a portion of the patient's dentition. The 3D virtual dental model may include at least one virtual abutment preparation. The virtual abutment preparation may be a virtual representation of a physical abutment preparation prepared by a dentist. In some embodiments, the virtual dental restoration design automation may also receive a mating 3D virtual dental model. The mating 3D virtual dental model may include at least a portion of the patient's dentition opposite the physical abutment preparation. The mating 3D virtual dental model may include at least one virtual antagonist corresponding to but on the opposite jaw from the at least one virtual abutment preparation. In some embodiments, the dentist may be a chairside dentist located in a dental office. In some embodiments, the step of receiving the 3D virtual dental model may be performed in a cloud computing environment.

[0023] In some embodiments, the 3D virtual dental model and the mating 3D virtual dental model may be generated by any process that scans a patient's dentition or a physical impression of the patient's dentition to generate a virtual 3D dental model of the patient's dentition. In some embodiments, the 3D virtual dental model and the mating 3D virtual dental model may be generated from an intraoral scan of the patient's dentition. In some embodiments, for example, an intraoral scan may be performed to generate two virtual dental models—a 3D virtual dental model with virtual abutment preparations and a mating 3D virtual dental model with virtual opponents. The intraoral scanning device may be, for example, handheld in some embodiments and may be used by a dentist, technician, or user to scan the patient's dentition. Standard intraoral scanning devices and associated hardware and software can then generate the virtual 3D dental model as a standard STL file or other suitable standard format. One example of an intraoral scanner may be the Itero® intraoral scanner offered by Align Technologies. Another example of an intraoral scanner may be the i700 intraoral scanner offered by Medit. Other intraoral scanners or other scanners and / or scanning technologies for generating a 3D virtual dental model of at least a portion of the patient's dentition may also be used. In some embodiments, the scanning process may generate, for example, an STL, PLY, or CTM file that may be suitable for use with dental design software, such as FastDesign™ dental design software offered by Glidewell Laboratories of Newport Beach, California. In some embodiments, the intraoral scan may be performed outside of a dental laboratory. For example, in some embodiments, the intraoral scan may be performed in a dental office. In some embodiments, the dentist / dental office may be part of a Dental Support Organization ("DSO"). A DSO may include one or more dentists working together.

[0024] In some embodiments, one or more steps disclosed herein may occur in near real time. For example, in some embodiments, one or more steps in the present disclosure may be performed while a patient is present at a dental clinic for treatment. Often, the patient may be under general or local anesthesia and seated in a treatment chair while a dentist prepares one or more physical abutment teeth and then scans at least a portion of the patient's dentition to image the prepared physical teeth and the portion of the patient's dentition and generate a 3D virtual dental model. In some embodiments, while the patient is seated in the treatment chair, the dentist may scan at least a portion of the patient's opposing teeth to generate a paired 3D virtual dental model of the opposing teeth / jaw. The scan may be performed using an intraoral or other scanner at the dental clinic while the patient is still seated in the chair and receiving treatment.

[0025] Once the 3D virtual dental model including one or more virtual preparations and the counterpart 3D virtual dental model have been generated, a dentist, staff member, or any other authorized user at the dental office can create a virtual case for the patient as part of the automated virtual dental restoration design and upload the virtual dental model (also known as a "scan"), which can be received for automated virtual restoration design. In some embodiments, the automated design can be performed in a cloud computing environment (the "cloud"). The virtual case may be stored or associated with information about both the particular patient and the treatment, for example, in a storage device or database. In some embodiments, that information may include patient and preparation information, such as, but not limited to, the patient's name, user-selectable preparation tooth number, user-selectable material, user-selectable preparation tooth shade, and the 3D virtual dental model itself.

[0026] In some embodiments, the 3D virtual dental model and the mating 3D virtual dental model may be provided to the automated dental restoration design process and system through a graphical user interface ("GUI") displayable on a client device by the cloud computing environment. In some embodiments, for example, the GUI may provide an interface that allows a client to log in to a dental restoration design server and upload a scanned virtual 3D dental model. In some embodiments, the client may be, for example, a dentist, a dental technician, or any other user. In some embodiments, the client may be located within a dental office.

[0027] In some embodiments, the cloud computing environment may receive the 3D virtual dental model from a client device, which may include, for example, a computing device in a dental office. Case creation and uploading may be performed through an interface, such as a graphical user interface ("GUI") displayed on the display of the client device to allow for entry of case information and uploading of the 3D virtual dental model. In some embodiments, the interface may be connected, for example, to one or more clouds or to one or more computer servers or other systems operated by dental laboratories and connected to dental offices via the Internet for storing case information. In some embodiments, the case is created, and in some embodiments, the information is provided manually by a dentist or other person at the dental office or automatically by scanning software used in the scanner. For example, in some embodiments, an Itero® intraoral scanner may scan a patient's dentition at the dental office and automatically open the case, enter case information, and upload the 3D virtual dental model.

[0028] Some embodiments of a computer-implemented method for automating virtual dental restoration design may include performing the automated virtual restoration design using a 3D virtual dental model. In some embodiments, the automated virtual restoration design can be performed while the patient is in the chair during a patient visit to a dental office. In some embodiments, the automated virtual restoration design can be performed in a cloud computing environment.

[0029] FIG. 2 illustrates an example overview of some embodiments. A dentist, dental technician, or other user located at a dental office 202 can open a new case 208 and use an intraoral scanner 206 to scan at least a portion of the patient's dentition, including at least one physical abutment tooth, which in some embodiments is associated with the case 208. In some embodiments, other intraoral scans of at least a portion of the patient's opposing dentition (i.e., the other jaw) can also be taken and associated with the same case 208. The intraoral scanner can generate a virtual dental model for each scan. For example, the intraoral scanner can generate a 3D virtual dental model for the dentition along with at least one physical abutment tooth and a matching 3D virtual dental model for the opposing dentition. In some embodiments, the intraoral scan 206 is first performed, and an order form 208 can be automatically generated. Once the intraoral scan is complete, in some embodiments, the 3D virtual dental model and the matching 3D virtual dental model can be sent to automated design 210.

[0030] In some embodiments, automated design 210 can execute in a cloud computing environment. In some embodiments, automated design 210 can determine the quality of a physical abutment preparation prepared by a dentist. If the physical abutment preparation is of acceptable quality and no issues are observed at 211, automated design 210 generates a virtual restoration, which in some embodiments can be displayed on a computing device display to a dentist, dental technician, or other user in dental office 202 for design confirmation (“DC”) 214. Design confirmation 214, in some embodiments, allows a dentist or the like to make adjustments to the generated virtual restoration and / or margin lines.

[0031] In some embodiments, the dentist, other user, etc. may make minor adjustments that can be applied to the virtual restoration. In some embodiments, the dentist, other user, etc. may make major adjustments. In some embodiments, minor and major changes can be applied on an ad-hoc basis. Major adjustments may include, for example, but are not limited to, adjusting margin lines. In some embodiments, major adjustments 222 each trigger automated design 210 to regenerate a new virtual restoration based on the major adjustments made. Once all adjustments are complete and the design is finalized by the dentist or user, the final virtual restoration design is transferred 224 to design machinability check 220. In some embodiments, the dentist, other user, etc. may simply accept the initially proposed virtual restoration without making any adjustments, which is then transferred 224 to design machinability check 220.

[0032] Design machinability check 220 can determine whether the generated virtual restoration is capable of automated milling. Design machinability check 220 can be located in a cloud computing environment. The cloud computing environment can be the same for both automated design 210 and design machinability check 220, or separate cloud computing environments can be used. If the virtual restoration is capable of automated milling, it can be sent to milling 216 for physical fabrication of the virtual restoration. In some embodiments, if design machinability check 220 passes, milling 216 can be automated milling. An example of automated milling can be found in U.S. Pat. No. 1,047,0853 to Leeson et al., which is incorporated herein by reference in its entirety. In some embodiments, if design machinability check 220 indicates that automated milling is not feasible, milling 216 can be manual milling. In some embodiments, milling 216 can be performed in the dental laboratory 204.

[0033] In some embodiments, if the automated design 210 identifies one or more issues 209 with the physical preparation tooth, the computer-implemented method may provide virtual guidance / feedback at 212, such as to a dentist and / or other user within the dental office 202. In some embodiments, the dentist may then adjust the physical preparation tooth, the physical antagonist, and / or a portion of the patient's dentition based on the virtual guidance / feedback and rescan (215) the patient's adjusted physical dentition, which may include one or more physical preparation teeth and antagonist teeth and / or dentition. The dentist or user may then re-upload the rescanned 3D virtual model of the rescanned 3D virtual dental model, which in some embodiments may include at least one rescanned virtual preparation tooth and / or at least one corresponding rescanned antagonist. The rescan may be added to the same order form 208 in some embodiments, and processing may resume as shown in FIG. 2 .

[0034] In some embodiments, upon receiving virtual guidance feedback 212 indicating one or more issues, the dentist / user simply accepts and submits (219) the 3D virtual dental model and any opposing 3D virtual dental models to a design lab technician 232 or other user, typically located in a dental laboratory 204. The design lab technician or other user can then determine one or more reduction areas on the virtual abutment tooth based on the issues arising from the automated design and design a virtual reduction coping as described in U.S. Patent No. 1,135,1015 to Leeson et al. (hereinafter '015). The design lab technician can then fabricate a physical reduction / guidance coping as described in '015 and send the physical reduction / guidance coping to the dentist or user at the dental office to provide physical feedback on which physical abutment tooth, opposing tooth, and / or surrounding dentition area to physically reduce. In some embodiments, the design technician can also design a virtual restoration for the virtual reduction abutment preparation and send the designed virtual restoration to design machinability confirmation 220 for subsequent fabrication of a physical restoration. In some embodiments, the design lab technician can use automated design 210 to generate a virtual restoration from the virtual reduction abutment preparation, the virtual reduction opponent, and / or the virtual reduction patient dentition. In some embodiments, the dental technician can manually design the virtual restoration.

[0035] FIG. 3 illustrates an overview of an example of dental restoration automation in some embodiments. A dentist, dental technician, or other user located in a dental office 302 can open a new case 308 and use an intraoral scanner 306 to scan at least a portion of the patient's dentition, including, in some embodiments, at least one physical abutment tooth, which is associated with the case 308. Other intraoral scans of at least a portion of the patient's opposing dentition (i.e., the other jaw) can also be taken and associated with the same case 308 in some embodiments. The intraoral scanner can generate virtual dental models for each scan. For example, the intraoral scanner can generate a 3D virtual dental model for the dentition with at least one physical abutment tooth and a counterpart 3D virtual dental model for the opposing dentition. In some embodiments, the intraoral scan 306 is performed first, allowing the order form 308 to be automatically generated. Once the intraoral scan is complete, in some embodiments, the 3D virtual dental model and the counterpart 3D virtual dental model can be sent to automated design 310.

[0036] In some embodiments, the automated design 310 can execute in a cloud computing environment. In some embodiments, the automated design 310 can determine the quality of a physical abutment preparation prepared by a dentist. If the physical abutment preparation is of acceptable quality and no issues are observed at 311, the automated design 310 generates a virtual restoration, and the generated virtual product can be displayed on a computing device display, in some embodiments, to a dentist, dental technician, or other user in the dental office 302 for design confirmation (“DC”) 314. Design confirmation 314, in some embodiments, allows a dentist or the like to make adjustments to the generated virtual restoration and / or margin lines, as described above with respect to FIG. 2 .

[0037] In some embodiments, the dentist, other user, etc. may make minor adjustments that can be applied to the virtual restoration. In some embodiments, the dentist, other user, etc. may make major adjustments. Major adjustments may include, for example, but are not limited to, adjusting margin lines. In some embodiments, major adjustments 322 trigger automated design 310 to regenerate a new virtual restoration based on the major adjustments made. In some embodiments, minor and major changes can be applied on an ad-hoc basis. Once all adjustments are complete and the design is finalized by the dentist or user, the final virtual restoration design is transferred to design machinability check 320 (324). In some embodiments, the dentist, other user, etc. may simply accept the initially proposed virtual restoration without making any adjustments, which is then transferred to design machinability check 320 (324).

[0038] In some embodiments, if the automated design 310 identifies one or more issues with the physical abutment preparation tooth (309), the computer-implemented method can transfer (309) the uploaded 3D virtual dental model, including one or more virtual abutment preparation teeth and antagonist / dentition 3D virtual dental models, to a design technician 316. In some embodiments, the design technician 316 may be located at, for example, the dental laboratory 304. In some embodiments, once the manual design is complete, the dental technician 316 can transfer the manually generated virtual restoration to design machinability check 320 and fabrication as described above. In some embodiments, the dental laboratory 304 can also provide feedback to the dentist and / or user regarding one or more issues with the identified physical abutment preparation tooth automated design 310. In some embodiments, the feedback can include one or more images or 3D models with any issues marked. In some embodiments, once the virtual restoration design is complete, the design technician 316 can provide the virtual restoration design for design machinability check 320 at 318.

[0039] The design machinability check 320 can determine whether the generated virtual restoration is capable of automated milling. The design machinability check 320 can be located in a cloud computing environment. The cloud computing environment can be the same for both the automated design 310 and the design machinability check 320, or separate cloud computing environments can be used. If the virtual restoration is capable of automated milling, it can be sent to automated milling 332 for physical fabrication of the virtual restoration. In some embodiments, if the design machinability check 320 passes, milling 316 can be automated milling. An example of automated milling can be found in U.S. Pat. No. 1,047,0853 to Leeson et al., which is incorporated by reference in its entirety. In some embodiments, if the design machinability check 320 indicates that automated milling is not feasible, milling 316 can be manual milling 336. The virtual restoration can be sent 334 to manual milling 336 in some embodiments. In some embodiments, the milling may be performed in a dental laboratory 304 .

[0040] In some embodiments, the steps of performing the automated virtual restoration design may include, for example, one or more of the following steps: decimating the 3D virtual dental model, meshing, segmenting, determining an occlusal orientation, determining a bite, localizing a preparation mold, determining a buccal orientation, determining a margin for at least one virtual preparation tooth, determining an insertion orientation for the virtual preparation tooth, determining a cement space for the virtual preparation tooth, generating a virtual restoration, and tensioning the virtual restoration to the margin. In some embodiments, one or more of the automated virtual restoration design steps may be performed on a 3D virtual model including the one or more virtual preparation teeth. In some embodiments, one or more of the automated virtual restoration design steps may be performed on a counterpart 3D virtual model including one or more counterpart virtual teeth opposing a corresponding or more virtual preparation teeth. In some embodiments, the one or more steps may be performed sequentially or in any other suitable order. In some embodiments, one or more steps may be excluded.

[0041] FIG. 4 illustrates one or more examples of automated virtual restoration design steps 400. In some embodiments, the one or more automated virtual restoration design steps may be performed in a cloud computing environment. In some embodiments, the steps for performing the automated virtual restoration design may include, for example, one or more of the following steps: decimating a 3D virtual dental model 402, meshing 404, segmenting 406, determining an occlusal direction 408, determining a bite 410, localizing a preparation mold 412, determining a buccal direction 414, determining a margin for at least one virtual preparation tooth 416, determining an insertion direction for the virtual preparation tooth 418, determining a cement space for the virtual preparation tooth 420, generating a virtual restoration 422 or generating a virtual bridge 424, and tensioning the virtual restoration to the margin 426, which may be performed sequentially or in any other suitable order. In some embodiments, one or more steps may be performed in any order. In some embodiments, one or more steps may be performed sequentially, for example, in the order shown in FIG. 4. In some embodiments, some steps may be omitted.

[0042] In some embodiments, the automated virtual restoration design may optionally include performing decimation. Decimation may include reducing the file size of the 3D virtual dental model. This may be achieved, in some embodiments, by reducing the number of polygons in the 3D virtual dental model. In some embodiments, the amount of decimation may be a user-configurable value that may, for example, sample a subset of polygons or points in the 3D virtual dental model. In some embodiments, decimation may be performed by selecting a subset of points that define the 3D virtual dental model. For example, in some embodiments, the computer-implemented method may select every second or third point in the 3D virtual dental model. In some embodiments, decimation may be performed while the patient is in the dental office. In some embodiments, decimation may be triggered when the number of polygons (in some embodiments, virtual triangles) in the virtual mesh exceeds a user-configurable threshold. In some embodiments, decimation may include combining two or more virtual triangles in the virtual mesh to reduce the number of virtual triangles in the mesh, adjusting the mesh to increase uniformity, and reducing the size of virtual triangles in areas of greater curvature. Figure 5(a) shows an example of an initial virtual mesh with more virtual triangles than a user-configurable threshold for decimation. Figure 5(b) shows an example of a decimated virtual mesh with fewer virtual triangles than a user-configurable threshold for decimation. Figure 5(c) shows an example of a portion of a virtual mesh 500 with one or more regions of increased curvature that have smaller virtual triangles 501 than other less curved regions. Other highly curved regions with smaller virtual triangles are also circled in Figure 5(c).

[0043] In some embodiments, the automated virtual restoration design may optionally include performing mesh repair. In some embodiments, mesh repair may include, for example, removing triangles, filling holes, and smoothing the virtual dental model. In some embodiments, mesh repair may be performed while the patient is in the dental office. In some embodiments, mesh repair may include correcting the triangulation of the mesh (grid), removing any self-intersections of the mesh, removing spikes and long, thin virtual triangles, removing tunnels, filling holes, removing empty points (not belonging to any virtual triangles), and removing isolated small mesh regions. In some embodiments, mesh repair may be performed during the patient's treatment in the dental office.

[0044] In some embodiments, the automated virtual restoration design may include automatically performing segmentation on the 3D virtual dental model. The segmentation may identify one or more virtual teeth, gums, and / or other features in the 3D virtual dental model. One or more examples of automatically performing segmentation on the 3D virtual dental model can be found in U.S. Patent Application No. 17 / 140,739 to Azernikov et al., which is incorporated herein by reference in its entirety. As described in that application, the segmentation may include, for example, receiving a 3D virtual model of patient scan data of at least a portion of the patient's dentition; generating a panoramic image from the 3D virtual model; labeling one or more regions of the panoramic image using a first trained neural network to provide a labeled panoramic image; mapping one or more regions of the labeled panoramic image to one or more corresponding coarse virtual surface triangle labels in the 3D virtual model to provide a labeled 3D virtual model; and segmenting the labeled 3D virtual model to provide a segmented 3D virtual model. Other examples of automatically performing segmentation on a 3D virtual dental model can also be found in U.S. Patent Application No. 16 / 451,968 to Nikolskiy et al., which is incorporated herein by reference in its entirety. In some embodiments, segmentation may be performed during the patient's treatment while the patient is in the dental clinic.

[0045] In some embodiments, one or more features can be automatically determined using a trained 3D deep neural network ("DNN") on a volumetric (voxel) representation. In some embodiments, the DNN can be a convolutional neural network ("CNN"), which is a network that uses convolution instead of typical matrix multiplication in at least one of the hidden layers of a deep neural network. A convolutional layer can calculate its output value by applying a kernel function to a subset of values from the previous layer. A computer-implemented method can train a CNN by adjusting the weights of the kernel function based on the training data. The same kernel function can be used to calculate each value in a particular convolutional layer.

[0046] FIG. 6 illustrates an example of a CNN in some embodiments. For ease of explanation, a 2D_CNN is shown. A 3D_CNN has a similar architecture but may have a three-dimensional kernel (x, y, and z axes) to provide a three-dimensional output after each convolution. A CNN may include one or more convolutional layers, such as a first convolutional layer 502. The first convolutional layer 502 may apply a kernel (also called a filter), such as kernel 504, across an input image, such as input image 503, and optionally apply an activation function to generate one or more convolutional outputs, such as first kernel output 508. The first convolutional layer 502 may include one or more feature channels. Application of a kernel, such as kernel 504, and optionally an activation function, may generate a first convolutional output, such as convolutional output 506. The kernel may then advance to the next set of pixels in input image 503 based on a stride length, and apply kernel 504 and optionally an activation function to generate a second kernel output. The kernel may proceed in this manner until it has been applied to all pixels in the input image 503. In this manner, the CNN may generate a first convolved image 506, which may include one or more feature channels. The first convolved image 506, in some embodiments, may include one or more feature channels, such as 507. In some cases, the activation function may be, for example, a RELU activation function. Other types of activation functions may also be used.

[0047] The CNN may also include one or more pooling layers, such as a first pooling layer 512. The first pooling layer may apply a filter, such as a pooling filter 514, to the first convolved image 506. Any type of filter may be used. For example, the filter may be a maximum filter (which outputs the maximum value of the pixels to which the filter is applied) or an average filter (which outputs the average value of the pixels to which the filter is applied). The one or more pooling layers may downsample and reduce the size of the input matrix. For example, the first pooling layer 512 may reduce / downsample the first convolved image 506 by applying a first pooling filter 514 to provide a first pooled image 516. The first pooled image 516 may include one or more feature channels 517. The CNN may optionally apply one or more additional convolutional layers (and activation functions) and pooling layers. For example, the CNN may apply a second convolutional layer 518 and, optionally, an activation function to output a second convolved image 520, which may include one or more feature channels 519. A second pooling layer 522 may apply a pooling filter to the second convolved image 520 to generate a second pooled image 524, which may include one or more feature channels. The CNN may include one or more convolutional layers (and activation functions) and one or more corresponding pooling layers. The output of the CNN may optionally be sent to a fully connected layer, which may be part of the one or more fully connected layers 530. The one or more fully connected layers may provide output predictions, such as output prediction 524. In some embodiments, the output prediction 524 may include, for example, labels of the teeth and surrounding tissue. In some embodiments, the output prediction 524 may include identification of one or more features in the 3D digital dental model.

[0048] In some embodiments, the automated virtual restoration design may include automatically determining an occlusal orientation. An example of automatically determining an occlusal orientation can be found in U.S. Patent Application No. 17 / 245,944 to Azernikov et al., which is incorporated herein by reference in its entirety. In some embodiments, determining an occlusal orientation may be performed while the patient is in the dental office.

[0049] In some embodiments, the occlusion direction can be determined automatically using an occlusion direction trained neural network. In some embodiments, the occlusion direction trained CNN may be a 3D_CNN trained using one or more 3D voxel representations, each representing a patient's dentition, optionally along with augmented data such as surface normals for each voxel. The 3D_CNN may perform 3D convolutions operating on 3D inputs using 3D kernels instead of 2D kernels. In some embodiments, the trained 3D_CNN receives 3D voxel representations with voxel normals. In some embodiments, an N×N×N×3 floating-point tensor may be used. In some embodiments, N may be, for example, 100. Other suitable values of N may also be used. In some embodiments, the trained 3D_CNN may include four levels of 3D convolutions and two linear layers. In some embodiments, the 3D_CNN may operate in the regression domain, regressing voxels representing a patient's dentition and their corresponding normals to the triplet X, Y, and Z coordinates of a unit occlusion vector. In some embodiments, the training set for the 3D_CNN may include one or more 3D voxel representations, each representing a patient's dentition. In some embodiments, each 3D voxel representation in the training set may include an occlusion direction manually marked by a user or by other techniques known in the art. In some embodiments, the training set may include tens of thousands of 3D voxel representations, each with a marked occlusion direction. In some embodiments, the training dataset may include 3D point cloud models with an occlusion direction marked in each 3D point cloud model. Thus, one occlusion direction for each image / model (3D voxel representation) of the patient's dentition is marked in the training dataset by a technician, and the training dataset may include tens of thousands of corresponding images / models (3D voxel representations) of the patient's dentition. In the training data, the coordinates of the unit occlusion vector may be, for example, in some embodiments, X 2 +Y 2 +Z 2 =1.

[0050] In some embodiments, the automated virtual restoration design may include automatically determining bite settings. In some embodiments, bite settings may be determined between a 3D virtual dental model including one or more virtual abutment preparations and a mating 3D virtual dental model including one or more corresponding virtual antagonists. In some embodiments, automatically determining bite settings for a 3D virtual dental model can be found in U.S. Patent Application No. 17 / 007922 to Chelnokov et al., which is incorporated herein by reference in its entirety. As described in the above application, in some embodiments, automatically determining the bite setting may include receiving first and second virtual jaw models, such as a 3D virtual dental model with virtual abutment preparations and a counterpart 3D virtual dental model with corresponding virtual opponents, determining a rough bite approximation of the first and second virtual jaw models, determining one or more initial bite positions of the first and second virtual jaw models from the rough approximation, determining one or more iterative bite positions of the first and second virtual jaw models for each of the one or more initial bite positions, determining a score for each iterative bite position, and outputting the bite setting based on the score. In some embodiments, determining the bite setting may be performed while the patient is at the dental clinic.

[0051] In some embodiments, the automated virtual restoration design may include automatically performing abutment preparation mold localization. An example of automatically performing mold localization can be found in U.S. Patent Application No. 17 / 245,944 to Azernikov et al., previously incorporated by reference. As described in that application, automatically performing mold localization may include determining a 3D center of a virtual abutment preparation using a neural network on an occlusally aligned 3D point cloud. In some embodiments, the abutment preparation mold localization may be performed while the patient is in the dental office.

[0052] In some embodiments, the 3D center of the digital abutment preparation mold can be determined automatically. For example, in some embodiments, the 3D center of the digital abutment preparation can be determined using a neural network on an occlusally aligned 3D point cloud. In some embodiments, the trained neural network can provide the 3D coordinates of the center of the digital abutment preparation bounding box. In some embodiments, the neural network can be any neural network capable of performing segmentation on a 3D point cloud. For example, in some embodiments, the neural network can be a PointNet++ neural network segmentation as described in this disclosure. In some embodiments, the digital abutment preparation mold can be determined by a sphere of fixed radius around the 3D center of the digital abutment preparation. In some embodiments, the fixed radius can be, for example, 0.8 cm for molars and premolars. Other suitable values for the fixed radius can be determined and used, for example, in some embodiments. In some embodiments, training the neural network can include using a sampled point cloud of the digital jaw (without augmentation) centered on the center of mass of the jaw. In some embodiments, the digital jaw point cloud can be oriented in a manner such that the occlusion direction is positioned vertically. In some embodiments, the computer-implemented method can train a neural network to determine a digital abutment preparation site / mold in a 3D digital dental model by using a training data set. The 3D digital dental model can include a 3D digital model of a point cloud of a patient's dentition, such as a digital jaw, which may include an abutment preparation site, along with one or more points within the margin line of the abutment preparation site marked by a user using an input device or any technique known in the art. In some embodiments, the training set can be tens of thousands of points. In some embodiments, the neural network can utilize segmentation during operation to return a bounding box that contains the selected points. In some embodiments, the segmentation used can be, for example, PointNet++ segmentation.

[0053] In some embodiments, the 3D center of the digital abutment forming mold can be determined automatically based on a flat depth map image of the jaw. In the training dataset, the location of the mold center may be determined as the geometric center of the margin marked by the technician. In some embodiments, for example, the final margin point from the finished case may be used. In some embodiments, the network receives a depth map image of the jaw from an occlusal view and returns the location (X, Y) of the mold center in pixel coordinates of the image. For training, a dataset containing depth map images and corresponding ground truth values—floating-point X and Y values—can be used. In some embodiments, the training set can be tens of thousands of images.

[0054] In some embodiments, the 3D center of the digital abutment forming mold may optionally be set manually by a user, hi some embodiments, the 3D center of the digital abutment forming mold may be set using any technique known in the art.

[0055] In some embodiments, the automated virtual restoration design may include automatically determining a buccal direction. In some embodiments, the 3D digital model may include a buccal direction. In some embodiments, the buccal direction may be manually set by a user. In some embodiments, the buccal direction may be determined using any technique known in the art. An example of automatically determining a buccal direction can be found in U.S. Patent Application No. 17 / 245,944, previously incorporated by reference. In some embodiments, automatically determining a buccal direction may include, for example, providing a 2D depth map image of the 3D virtual model mesh to a trained 2D convolutional neural network ("CNN"), such as GoogleNet Inception v3. In some embodiments, the trained 2D CNN operates on an image representation. In some embodiments, determining the buccal direction may be performed while the patient is at the dental clinic.

[0056] In some embodiments, the trained 2D CNN operates on an image representation. In some embodiments, the buccal direction may be determined by providing a 2D depth map image of the 3D digital model mesh to the trained 2D CNN. In some embodiments, the method may optionally include generating a 2D image from the 3D digital model. In some embodiments, the 2D image may be a 2D depth map. The 2D depth map may include a 2D image including, at each pixel, the distance from an orthographic camera to an object along a line passing through the pixel. The object may, for example, in some embodiments, be the surface of a digital jaw model. In some embodiments, the input may include an object, such as a 3D digital model of the patient's dentition, e.g., a jaw ("digital model"), and a camera orientation. In some embodiments, the camera orientation may be determined based on an occlusal direction. The occlusal direction is normal to the occlusal plane, which can be determined for the digital model using any technique known in the art. Alternatively, in some embodiments, the occlusal direction may be specified by a user manipulating the digital model on a display using an input device, such as a mouse or touchscreen, as described herein. In some embodiments, the occlusal direction can be determined using the occlusal axis technique described, for example, in U.S. Patent Application No. 16 / 451968 to Nikolskiy et al. (U.S. Patent Application Publication No. 20200405464), the entire contents of which are incorporated herein by reference.

[0057] The 2D depth map can be generated using any technique known in the art, such as z-buffer or ray tracing. For example, in some embodiments, the computer-implemented method may initialize, for example, the depth of each pixel (j,k) to a maximum length and the pixel color to a background color. For each pixel in a projection of a polygon onto a digital surface, such as a 3D digital model, the computer-implemented method may determine the depth z of the polygon at (x,y) corresponding to pixel (j,k). If z<the depth of pixel (j,k), then the pixel's depth is set to depth z. The "z" may refer to the convention that the central axis of a camera's field of view is in the direction of the camera's z-axis, but does not necessarily refer to the absolute z-axis of the scene. In some embodiments, the computer-implemented method may also, for example, set the pixel color to some color other than the background color. In some embodiments, the polygon may be, for example, a digital triangle. In some embodiments, the map depth may be per pixel. FIG. 7 shows an example of a 2D depth map of a digital model in some embodiments.

[0058] In some embodiments, the 2D depth map image may include a von Mises average of 16 rotated versions of the 2D depth map. In some embodiments, the buccal direction may be determined after determining the occlusal direction and the 3D center of the digital abutment mold. In some embodiments, the 2D depth map image may be of a portion of the digital jaw around the digital abutment mold. In some embodiments, regression may be used to determine the buccal direction. In some embodiments, the 2D_CNN may include, for example, GoogleNet Inception v3, which is well known in the art. In some embodiments, the computer-implemented method may train a buccal-trained neural network using a training dataset. In some embodiments, the training dataset may include, for example, the buccal direction marked in a 3D point cloud model. In some embodiments, the training dataset may include tens of thousands to hundreds of thousands of images. In some embodiments, the computer-implemented method preprocesses the training dataset by converting each training image into a 2D depth map as previously disclosed and training the 2D_CNN using the 2D depth map, for example.

[0059] In some embodiments, the occlusal direction, buccal direction, and / or abutment preparation mold area may, for example, provide a normalized orientation of the 3D virtual model. For example, the occlusal direction is normal to the occlusal plane, the virtual abutment preparation mold may be the area around the virtual abutment preparation teeth, and the buccal direction may be the direction toward the cheeks in the mouth. Figure 8 shows an example of a 3D virtual model 600 of at least a portion of a patient's dentition, which may include, for example, a virtual jaw 602 including virtual abutment preparation teeth 604. The 3D virtual model 600 may include an occlusal direction 606, a virtual abutment preparation mold area 608, and a buccal direction 610.

[0060] In some embodiments, the automated virtual restoration design may include automatically determining an adjustable margin line of the virtual abutment preparation. An example of automatically determining an adjustable margin line of the virtual abutment preparation can be found in U.S. Patent Application No. 17 / 245,944 to Azernikov et al., which is incorporated herein by reference in its entirety.

[0061] In some embodiments, the computer-implemented method can determine the proposed margin line by receiving a 3D digital model having a digital abutment formation site and determining an internal representation of the 3D digital model using a trained neural network of internal representations.

[0062] Some embodiments of the computer-implemented method may include determining an inner representation of the 3D digital model using a trained neural network of inner representation. In some embodiments, the trained neural network of inner representation may include an encoder neural network. In some embodiments, the trained neural network of inner representation may include a neural network for 3D point cloud analysis. In some embodiments, the trained neural network of inner representation may include a trained hierarchical neural network ("HNN"). In some embodiments, the HNN may include a PointNet++ neural network. In some embodiments, the HNN may be any message-passing neural network that operates on any geometric structure. In some embodiments, the geometric structure may include a graph, a mesh, and / or a point cloud.

[0063] In some embodiments, the computer-implemented method may use an HNN such as PointNet++ for encoding. PointNet++ is described in Charles R. Qi, Li Yi, Hao Su, and Leonidas J. Guibas, "PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space," Stanford University, June 2017, which is incorporated herein by reference in its entirety. A hierarchical neural network, for example, may process a set of sampled points in a metric space in a hierarchical manner. In some embodiments, an HNN such as PointNet++ or other HNNs may be implemented by determining a local structure induced by a metric. In some embodiments, an HNN such as PointNet++ or other HNNs may be implemented by first partitioning a set of points into two or more overlapping local regions based on a distance metric. The distance metric may be based on a basis space. In some embodiments, local features may be extracted. For example, in some embodiments, a granular geometric structure from small local neighborhoods may be determined. Features from small local neighborhoods may be grouped into larger units in some embodiments. In some embodiments, larger units can be processed to provide higher-level features. In some embodiments, the process is repeated until all features for the entire point set are obtained. Unlike volumetric CNNs, which scan space with a fixed stride, the local receptive fields in HNNs such as PointNet++ or other HNNs depend on both the input data and the metric. Also, as opposed to CNNs that scan vector spaces independent of the data distribution, the sampling strategy in HNNs such as PointNet++ or other HNNs generates receptive fields in a data-dependent manner.

[0064] In some embodiments, an HNN such as PointNet++ or other HNNs can use, for example, a local feature learner to determine how to partition local features and partition abstract sets of points or local features. In some embodiments, the local feature learner can be, for example, PointNet or any other suitable feature learner known in the art. In some embodiments, the local feature learner can process, for example, an unordered set of points to perform semantic feature extraction. The local feature learner can abstract one or more sets of local points / features into a higher-level representation. In some embodiments, the HNN can apply the local feature learner recursively. For example, in some embodiments, PointNet++ can recursively apply PointNet to nested partitions of an input set.

[0065] In some embodiments, the HNN can define partitions of overlapping point sets by defining each partition as a neighborhood sphere in Euclidean space with parameters that may include, for example, centroid location and scale. Centroids can be selected from the input set by, for example, farthest point sampling, as is well known in the art. One advantage of using an HNN can include, for example, efficiency and effectiveness, since local receptive fields can depend on the input data and metrics. In some embodiments, the HNN can exploit neighborhoods at multiple scales, which can enable, for example, robustness and detailed capture.

[0066] In some embodiments, the HNN may include hierarchical point set feature learning. The HNN builds hierarchical groupings of points, e.g., in some embodiments, it may abstract larger local regions along the hierarchy. In some embodiments, the HNN may include multiple levels of set abstraction. In some embodiments, the set of points is processed at each level and abstracted to generate a new set with fewer elements. In some embodiments, the set abstraction level may include three layers: a sampling layer, a grouping layer, and a local feature learner layer. In some embodiments, the local feature learner layer may be, for example, PointNet. The set abstraction level may take input of an N×(d+C) matrix from N points with d-dim coordinates and C-dim point features, and output an N′×(d+C′) matrix of N′ subsampled points with d-dim coordinates and a new C′-dim feature vector that may summarize the local background, for example, in some embodiments.

[0067] The sampling layer, in some embodiments, can select or sample a set of points from the input points. The HNN, for example, in some embodiments, can define these selected / sampled points as centroids of local regions. For example, in some embodiments, the HNN can select or sample a set of input points {x1, x2, . . . , x n}, x ij is the set {x i1 ,x i2 ,···,x ij-1} to the point {x i1 ,x i2 ,···,x im Iterative farthest point sampling (FPS) can be used to select a small set of {}. This can advantageously give better coverage of the entire point set, for example, considering the same centroid number, as opposed to random sampling. This can also advantageously generate receptive fields in a data-dependent manner, for example, for convolutional neural networks (CNNs) that scan a vector space independent of the data distribution.

[0068] The grouping layer can determine one or more local region sets by determining neighboring points around each centroid, for example, in some embodiments. In some embodiments, the input to this layer can be a set of points of size N×(d+C) and the coordinates of the centroids, having size N′×d. In some embodiments, the output of the grouping layer can include clusters of point sets, for example, having size N′×K×(d+C). Each cluster can correspond to a local region, for example, in some embodiments, where K is the number of points in the neighborhood of the centroid point. In some embodiments, K can vary between clusters. However, the next layer—the PointNet layer—can convert, for example, the flexible number of points into fixed-length local region feature vectors. The neighborhood can be defined, for example, by a metric distance, in some embodiments. By performing a ball query, for example, in some embodiments, all points within a radius around a query point can be determined. An upper bound on K can be set. In an alternative embodiment, a K-nearest neighbor (kNN) search can be used. kNN can determine a fixed number of neighboring points. However, the local neighborhood of a ball query can guarantee a fixed region scale, making one or more local region features more generalizable across space, which in some embodiments may be preferable for, for example, semantic point labeling or other tasks requiring local pattern recognition.

[0069] In some embodiments, the local feature learner can encode the local region patterns into feature vectors. For example, let X=(M, d) be a metric in a Euclidean space X n Let M ⊆ R be a discrete metric space inherited from n If M is a set of points and d is a distance metric, then the local feature learner layer can determine a function f that takes X as input and outputs semantically interesting information about X. The function f can be a classification function that assigns a label to X or a segmentation function that assigns pointwise labels to each element of M.

[0070] Some embodiments may use PointNet as a local feature learner layer, which is i ∈R d The unordered set of points {x1,x2,...,x n}, for example, a set of points is given as

number

[0071] In some embodiments, γ and h may be, for example, a multilayer perceptron (MLP) network or other suitable alternatives known in the art. The function f may be invariant to input point permutations, e.g., in some embodiments, it may approximate any continuous set function. The response of h may, in some embodiments, be interpreted as a spatial encoding of the points. PointNet is described in "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 77-85, by R. Q. Charles, H. Su, M. Kaichun, and L. J. Guibas, which is incorporated herein by reference in its entirety.

[0072] In some embodiments, the local feature learner layer can receive N' local region points. The data size can be, for example, N' x K x (d + C). In some embodiments, each local region is abstracted at the output by a local feature that encodes, for example, its centroid and the neighborhood of the centroid. The output data size can be, for example, N' x (d + C). The coordinates of points in the local region can, in some embodiments, be transformed to a local frame relative to the centroid position. For i = 1, 2,..., K and j = 1, 2,..., d,

number

number

[0073] In some embodiments, the local feature learner can address non-uniform density in the input point set, for example, via a density adaptation layer. The density adaptation layer can learn to synthesize features for regions at different scales when the input sampling density varies. In some embodiments, the density adaptation hierarchical network is, for example, a PointNet++ network. The density adaptation layer may include, for example, multi-scale grouping ("MSG") or multi-resolution grouping ("MRG") in some embodiments.

[0074] In MSG, multi-scale patterns can be captured in some embodiments by applying a grouping layer at different scales and subsequently extracting features for each scale. Extracting features for each scale can be performed, for example, by utilizing PointNet in some embodiments. In some embodiments, features at different scales can be concatenated to provide multi-scale features, for example. In some embodiments, the HNN can learn optimized multi-scale feature synthesis through training. For example, random input dropout can be used, where random input points are dropped input points with randomized probability. For example, a dropout ratio of θ uniformly sampled from [0, p], where p is less than or equal to 1, can be used in some embodiments. For example, p can be set to 0.95 in some cases to prevent the generation of an empty set of points. Other suitable values can be used, for example, in some embodiments.

[0075] In MRG, for example, level Li A feature of a region of may be a combination of two vectors, the first vector being, for example, in some embodiments, a vector of lower level L i-1 The second vector is obtained by aggregating features in each sub-region from the first vector. This can be achieved using a set abstraction level. In some embodiments, the second vector may be features obtained by directly processing the original points of the local region, for example, using a single PointNet. If the local region density is low, the second vector may be weighted more heavily in some embodiments because the first vector contains fewer points and includes sampling defects. If the local region density is high, the first vector may be weighted more heavily in some embodiments because, for example, the first vector may provide finer details due to inspection at a higher resolution, recursively at a lower level.

[0076] In some embodiments, point features can be propagated for set segmentation. For example, in some embodiments, a hierarchical propagation strategy can be used. In some embodiments, feature propagation involves propagating point features to N l ×(d+C) points to N l-1 It may include a step of propagating up to N points. l-1 and N l (N l is N l-1 ) are the input and output of the point set size at set abstraction level l. In some embodiments, feature propagation is performed using N l-1 In the coordinates of N points l This can be achieved by interpolating the feature values f of points N. In some embodiments, for example, an inverse distance audible average based on k nearest neighbors may be used (p=2, k=3 in the following equations, other suitable values may be used). l-1The imputed features for may be connected by skip-connected point features from the set abstraction level, for example, in some embodiments. In some embodiments, for example, the connected features may be passed through a unit PointNet, which may be similar to one-by-one convolutions in a convolutional neural network. Shared fully connected and ReLU layers may be applied to update the feature vectors of each point, for example, in some embodiments. In some embodiments, the process may be repeated until the propagation features back to the original set of points are determined.

number

[0077] In some embodiments, the computer-implemented method may implement one or more neural networks disclosed or known in the art. Any specific structures and values for one or more neural networks and any other features disclosed herein are provided by way of example only, and any suitable variations or equivalents may be used. In some embodiments, the one or more neural network models may be implemented based on the Pytorch geometry package, for example.

[0078] 9(a) and 9(b) illustrate an example of an HNN in some embodiments. The HNN includes a hierarchical point set feature learner 702, the output of which can be used to perform segmentation 704 and / or classification 706. The example hierarchical point set feature learner 702 uses points in 2D Euclidean space as an example, but is capable of operating in three dimensions on input 3D images. As shown in the example of FIG. 9(a), the HNN can receive an input image 708 at (N, d+C) and perform a first sampling and grouping operation 710 to generate, for example, a first sampled and grouped image 712 at (N1, K, d+C). The HNN can then provide the first sampled and grouped image 712 to PointNet at 714 to provide a first abstracted image 716 at (N1, d+C1). The first abstracted image 716 may be sampled and grouped 718 to provide a second sampled and grouped image 720 at (N2, K, d+C1). The second sampled and grouped image 720 may be provided to a PointNet neural network 722 to output a second abstracted image 724 at (N2, d+C2).

[0079] In some embodiments, the second abstracted image 724 can be segmented by the HNN segmentation 704. In some embodiments, the HNN segmentation 704 can take the second abstracted image 724 and perform a first interpolation 730, the output of which can be concatenated with the first abstracted image 716 to provide a first complementary image 732 at (N,d+C+C). The first complementary image 732 can be provided to a unit PointNet at 734 to provide a first segmented image 736 at (N,d+C). The first segmented image 736 can be interpolated at 738, the output of which can be concatenated with the input image 708 to provide a second complementary image 740 at (N,d+C+C). The second complementary image 740 can be provided to a unit PointNet 742 to provide a segmented image 744 at (N,k). The segmented image 744 can provide, for example, a pointwise score.

[0080] 9(b), the second abstracted image 724, in some embodiments, can be classified by an HNN classifier 706. In some embodiments, the HNN classifier can take the second abstracted image 724 and provide it to a PointNet network 760, the output 762 of which can be provided to one or more fully connected layers, such as a connection layer 764, the output of which can provide a classification score 766.

[0081] Some embodiments of the computer-implemented method may include using a quantile-trained neural network to determine the proposed margin line from the underlying margin line and the inner representation of the 3D digital model.

[0082] In some embodiments, the basal margin line may be pre-computed once per network type. In some embodiments, the network type may include molars and premolars. Other suitable network types may be used in some embodiments, for example. In some embodiments, the network type may include other types. In some embodiments, the same basal margin line may be used as the initial margin line for each scan. In some embodiments, the basal margin line may be three-dimensional. In some embodiments, the basal margin line may be determined based on margin lines from the training dataset used to train the inner representation trained neural network and the quantile trained neural network. In some embodiments, the basal margin line may be a pre-computed arithmetic mean or common mean of the training dataset margin lines. In some embodiments, any type of arithmetic mean or common mean may be used.

[0083] In some embodiments, the margin line proposal may be a free-form margin line proposal. In some embodiments, the quantile-trained neural network may include a decoder neural network. In some embodiments, the decoder neural network can connect the inner representations by specific point coordinates to perform guided decoding. In some embodiments, the guided decoding can generate closed surfaces as described in "A Papier-Mache Approach to Learning 3D Surface Generation," T. Groueix, M. Fisher, V.G. Kim, B.C. Russell, and M. Aubry, 2018, IEEE / CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 216-224, which is incorporated herein by reference in its entirety.

[0084] In some embodiments, the decoder neural network may include a deep neural network ("DNN"). Referring now to Figure 10, which is a high-level block diagram illustrating the structure of a deep neural network (DNN) 800 according to some embodiments of the present disclosure. The DNN 800 includes multiple layers N i , N h,1 , N h,l-1 , N h,l , N o The first layer N i is the input layer into which one or more dentition scan datasets can be input. The final layer N o is the output layer. The deep neural network used in the present disclosure may output probabilities and / or full 3D margin line proposals. For example, the output may be a probability vector containing one or more probability values for each feature or aspect of the dental model belonging to a category. Furthermore, the output may be a margin line proposal.

[0085] Each layer N may contain multiple nodes that connect to each node in the next layer N+1. For example, layer N h,l-1 Each operation node in layer N h,lConnect to each operation node of the input layer N i and the output layer N o Layer N between h,1 , N h,l-1 , N h,l is a hidden layer. The nodes of the hidden layer are denoted as "h" in FIG. 10 and may be hidden variables. In some embodiments, the DNN 800 may include multiple hidden layers, e.g., 24, 30, 50 layers, etc.

[0086] In some embodiments, the DNN 800 may be a deep feedforward network. The DNN 800 may be a convolutional neural network, which is a network that uses convolutions instead of general matrix multiplication in at least one hidden layer of the deep neural network. The DNN 800 may be a generative neural network or a generative adversarial network. In some embodiments, training may supervise the training process of the deep neural network using a training dataset with labels. The labels are used to map features to probability values in a probability vector. Alternatively, training may be performed using an unstructured and unlabeled training dataset to train a generative deep neural network in an unsupervised manner, without necessarily requiring a labeled training dataset.

[0087] In some embodiments, the DNN may be a multi-layer perceptron ("MLP"). In some embodiments, the MLP may include four layers. In some embodiments, the MLP may include a fully connected MLP. In some embodiments, the MLP utilizes BatchNorm normalization.

[0088] FIG. 11 shows a diagram of a computer-implemented method for automatic margin line proposal in some embodiments, by way of example. In some embodiments, before beginning margin line proposal for any 3D digital model, the computer-implemented method may pre-calculate 901 the base margin line 903 in three dimensions, with each point of the base margin line 903 having a 3D coordinate, such as coordinate 905. The computer-implemented method may receive 902 a 3D digital model of at least a portion of a jaw. The 3D digital model may, in some embodiments, be in the form of a 3D point cloud. The 3D digital model may include, for example, a preparation tooth 904. The computer-implemented method may determine 908 an internal representation of the 3D digital model using an internal representation trained neural network 906. In some embodiments, the internal representation trained neural network 906 may be a neural network that performs grouping and sampling 907 and other operations on the 3D digital model, such as, for example, an HNN in some embodiments. In some embodiments, the computer-implemented method can use a quantile-trained neural network 910 to determine the proposed margin line from the base margin line 903 and the inner representation 908 of the 3D digital model. In some embodiments, the quantile-trained neural network can, for example, provide one or more three-dimensional quantile values 912 to the points on the digital surface of the base margin line 903.

[0089] In some embodiments, the quantile-trained neural network can determine margin line displacements in three dimensions from the base margin line. In some embodiments, the quantile-trained neural network uses BilateralChamferDistance as a loss function. In some embodiments, the computer-implemented method can move one or more points of the base margin line by the displacement to provide a proposed margin line. FIG. 12 shows an illustration of some embodiments of an example of adjusting a base margin line 1002 in a 3D digital model 1000. In this example, one or more base margin line points, such as base margin line point 1004, can be displaced by a displacement value and direction 1006. Other base margin line points can be similarly adjusted by their corresponding displacement values and directions, for example, to form a proposed margin line 1008.

[0090] Figure 13(a) shows an example of a proposed digital margin line 1104 for a digital abutment preparation tooth 1102 in a 3D digital model 1105. As can be seen, the margin line proposal can occur even when the margin line is partially or completely covered by gums, blood, saliva, or other elements. Figure 13(b) shows another example of a proposed digital margin line 1106 for a digital abutment preparation tooth 1108 in a 3D digital model 1110. In some embodiments, the proposed margin line is displayed on the 3D digital model and can be manipulated by a user, such as a dental technician or doctor, using an input device to make adjustments to the proposed margin line.

[0091] In some embodiments, the inner representation trained neural network and the quantile trained neural network can be trained using the same training dataset. In some embodiments, the training dataset may include one or more training samples. In some embodiments, the training dataset may include 70,000 training samples. In some embodiments, each of the one or more training samples may include an occlusal direction, abutment preparation die center, and a buccal direction as normalized positioning and orientation for each sample. In some embodiments, the occlusal direction, abutment preparation die center, and a buccal direction may be set manually. In some embodiments, the training dataset may include target margin lines on the surfaces of the uncropped digital jaw and corresponding cropped digital surfaces. In some embodiments, the target margin lines may be prepared by a dental technician. In some embodiments, the training may use regression. In some embodiments, the training may include comparing proposed margin lines with the target margin lines using a loss function. In some embodiments, the loss function may be a Chamfer loss function. In some embodiments, the Chamfer loss function is

number

[0092] In some embodiments, training may be performed on a computing system that may include at least one graphics processing unit ("GPU"). In some embodiments, the GPU may include, for example, two 2080-Ti Nvidia GPUs. Other suitable GPU types, numbers, and equivalents may also be used.

[0093] In some embodiments, the computer-implemented method may be performed automatically. Some embodiments may further include displaying a free-form margin line on the 3D digital model. In some embodiments, the free-form margin line is adjustable by a user using an input device.

[0094] In some embodiments, an adjustable margin line may be displayed to the dentist or other user for initial adjustment. In some embodiments, the adjustment may include moving one or more portions of the margin line based on input from the dentist or other user. In some embodiments, the adjustment may include discarding the adjustable margin line and allowing the dentist to manually provide a margin line. In some embodiments, the computer-implemented method displays at least a portion of a 3D virtual dental model of the patient's dentition and the proposed automatically determined margin line, and allows the dentist or other user to modify the determined margin line. FIG. 14 shows an example of a proposed determined margin line 772 in a GUI 774 for a virtual abutment preparation tooth 775 in a 3D virtual dental model 776. In some embodiments, determining the adjustable margin line occurs before generating the 3D virtual dental restoration. Thus, during initial adjustments to the margin line, the 3D virtual dental restoration does not appear, thereby allowing the proposed (determined) margin line to be visible. In some embodiments, the GUI 774 provides virtual handles 778 to allow the user to adjust the automatically determined margin line. This can advantageously allow, for example, correction of the automatically determined margin line. In some embodiments, the step of automatically determining the margin line can be performed while the patient is at the dental office.

[0095] In some embodiments, the automated virtual restoration design may include determining an insertion direction of the restoration relative to the abutment tooth based on an adjustable margin line. An example of automatically determining an insertion direction based on an adjustable margin line can be found in U.S. Patent Application No. 16 / 918,586 to Leeson et al., which is incorporated herein by reference in its entirety. In some embodiments, determining the insertion direction may be performed while the patient is in the dental office.

[0096] In some embodiments, the automated virtual restoration design may include determining an inner surface of the virtual restoration based on the cement space. One or more examples of automatically determining an inner surface of a virtual restoration based on the cement space for a 3D virtual dental model can be found in U.S. Patent Application No. 16 / 918,586 to Leeson et al., which is incorporated herein by reference in its entirety. In some embodiments, the determining the inner surface of the virtual restoration based on the cement space may be performed while the patient is in the dental office. In some embodiments, the cement space may include the space between the physical abutment preparation and the physical restoration. In some embodiments, the cement space may include determining the inner surface of the virtual restoration. In some embodiments, the inner surface may include an offset from the outer surface of the virtual restoration, the offset comprising a cement gap. In some embodiments, occupying the cement space may include providing space for cement along one or more horizontal and vertical planes of the virtual restoration around the virtual margin. In some embodiments, the automated virtual restoration design may include tool radius compensation for a milling tool. In some embodiments, the determining the inner surface of the virtual restoration based on the cement space may be performed while the patient is in the dental office.

[0097] In some embodiments, the automated virtual restoration design may include automatically generating a 3D virtual restoration based on an adjustable margin line. Examples of automatically generating a 3D virtual restoration can be found in U.S. Patent No. 1,1291,532 to Azernikov et al. and U.S. Patent No. 1,100,7040 to Azernikov et al., each of which is incorporated herein by reference in its entirety. In some embodiments, the automatically generating a 3D virtual restoration may be performed while the patient is in the dental office. In some embodiments, the 3D virtual restoration may include a virtual crown. In some embodiments, the 3D virtual restoration may include a virtual bridge.

[0098] Some embodiments may include generating a virtual 3D dental prosthesis model based on the virtual 3D dental model using a trained deep neural network. Some embodiments may include automatically generating a 3D digital dental prosthesis model (virtual 3D dental prosthesis model) in the 3D digital dental model using a trained generative deep neural network. One example of generating a dental prosthesis using a deep neural network is described in U.S. Patent Application No. 15 / 925,078, now U.S. Patent No. 11,007,040, which is incorporated herein by reference in its entirety. Another example of generating a dental prosthesis using a deep neural network is described in U.S. Patent Application No. 15 / 660,073, which is incorporated herein by reference in its entirety.

[0099] Exemplary embodiments of methods and computer-implemented systems for generating a 3D model of a dental prosthesis using a deep neural network are described herein. Particular embodiments of the method may include training, with one or more computing devices, a deep neural network to generate a first 3D dental prosthesis model using a training dataset, receiving, with the one or more computing devices, patient scan data representing at least a portion of the patient's dentition, and generating, with the trained deep neural network, the first 3D dental prosthesis model based on the received patient scan data.

[0100] The training data set may include a dentition scan data set having abutment preparation site data and a dental prosthesis data set. The abutment preparation sites relative to the gum line may be defined by abutment preparation margins or margin lines relative to the gums. The dental prosthesis data set may include scanned prosthesis data associated with each abutment preparation site in the dentition scan data set.

[0101] The scanned prosthesis may be a scan of a real patient crown created based on a library dentition, which may have 32 or more dentition forms. The dentition scan dataset with abutment preparation site data may include scanned data of a real abutment preparation site from the scanned dentition of the patient.

[0102] In some embodiments, the training dataset may include a natural dentition scan dataset with digitally fabricated abutment preparation site data and a natural dental prosthesis dataset, which may include segmented tooth data associated with each digitally fabricated abutment preparation site in the dentition scan dataset. The natural dentition scan dataset may have two main components. The first component is a dataset including scanned dentition data of the patient's natural teeth. The data in the first component includes all of the patient's teeth in their natural, unmodified digital state. The second component of the natural dentition scan data is a missing teeth dataset in which one or more teeth have been removed from the scanned data. In place of the missing teeth, deep neural network-fabricated abutment preparation sites may be placed in the removed tooth sites. This process generates two sets of dentition data: complete, unmodified dentition scan data of the patient's natural teeth, and a missing teeth dataset (natural dental prosthesis dataset) in which one or more teeth have been digitally removed from the dentition scan data.

[0103] In some embodiments, the method further includes generating a full arch form digital model and segmenting each tooth in the full arch form to generate natural crown data for use as training data. The method may also include training another deep neural network to generate a second 3D dental prosthesis model using the natural dentition scan dataset with digitally fabricated abutment preparation site data and the natural dental prosthesis dataset, generating the second 3D dental prosthesis model based on the received patient scan data using the other deep neural network, and blending features of the first and second 3D dental prosthesis models together to generate a blended 3D dental prosthesis model.

[0104] FIG. 15 illustrates a process 1200 for generating a dental prosthesis using a deep neural network (DNN). Process 1200 begins at 1205, in which dentition scan data sets are received or imported into a database. The dentition scan data sets may include one or more scan data sets of a real patient's dentition with dental preparation sites and laboratory-generated (non-DNN-generated) dental prostheses created for those preparation sites. A dental preparation site (also called a preparation or prepared tooth) is a single tooth, multiple teeth, or an area of a tooth prepared to receive a dental prosthesis (e.g., a crown, bridge, inlay, etc.). A laboratory- or non-DNN-generated dental prosthesis is a dental prosthesis designed primarily by a dental technician. Furthermore, a laboratory-generated dental prosthesis can be designed based on a dental template library containing multiple dental restoration templates. Each tooth in an adult's mouth may have one or more dental restoration templates in the dental template library.

[0105] In some embodiments, the received dentition scan data set having dental abutment preparation sites may include scan data of a real patient's dentition having one or more dental abutment preparation sites. The abutment preparation sites may be defined by abutment preparation margins. The received dentition scan data set may also include scan data of dental prostheses once the dental prostheses have been placed in their corresponding dental abutment preparation sites. This data set may also be referred to as a dental prosthesis data set. In some embodiments, the dental prosthesis data set may include scan data of technician-created prostheses before they are placed.

[0106] In some embodiments, each received dentition scan data set may optionally be pre-processed before using the data set as input for the deep neural network. Dental scan data is typically a 3D digital image or file representing one or more portions of a patient's dentition. The 3D digital image (3D scan data) of the patient's dentition can be obtained by intraoral scanning of the patient's mouth. Alternatively, a scan of an impression or physical model of the patient's teeth may be performed to generate the 3D scan data of the patient's dentition. In some embodiments, the 3D scan data may be converted into a 2D data format, for example, using a 2D depth map and / or snapshots.

[0107] At 1210, the deep neural network can be trained (e.g., by a computer-implemented method or other process) using a dentition scan dataset that includes scan data of real dental abutment preparation sites and their corresponding laboratory-generated dental prostheses—post-installation and / or pre-installation. The combination of the datasets of real dental abutment preparation sites and their corresponding laboratory-generated dental prostheses can be referred to herein as a laboratory-generated dentition scan dataset. In some embodiments, the deep neural network can be trained using only the laboratory-generated dentition scan dataset. In other words, the training data includes only laboratory-generated dental prostheses created based on one or more dental restoration library templates.

[0108] A dental template in a dental restoration library is designed with specific features for a particular tooth (e.g., tooth number 3) and is therefore considered an optimal restoration model. Generally, a typical adult mouth has 32 teeth. Therefore, a dental restoration library may have at least 32 templates. In some embodiments, each tooth impression may have one or more specific features (e.g., sidewall size and shape, buccal and lingual cusps, occlusal surfaces, and buccal and lingual arcs, etc.) that may be unique to one of the 32 teeth. For example, each tooth in the restoration library is designed to include features, landmarks, and orientations that may best match the adjacent teeth, surrounding gingiva, and the tooth's position and location within the dental arch form. In this way, a deep neural network can be trained to recognize specific features (e.g., sidewall size and shape, cusps, grooves, pits, etc.) that may be salient for a particular tooth and their relationships (e.g., intercusp distance).

[0109] In some embodiments, a computer-implemented method or any other process may train a deep neural network to recognize that one or more dentition categories are present or identified in a training dataset based on an output probability vector. For example, the training dataset may include a large number of depth maps representing a patient's maxilla and / or a large number of depth maps representing a patient's mandible. The computer-implemented method or any other process may use the training dataset to train a deep neural network to recognize each individual tooth in a dental arch form. Similarly, the deep neural network may map a depth map of the mandible to a probability vector containing probabilities of the depth map belonging to the maxilla and the mandible, where the probability of the depth map belonging to the mandible is the highest in the vector or substantially higher than the probability of the depth map belonging to the maxilla.

[0110] In some embodiments, a computer-implemented method or other process can train a deep neural network to generate a complete 3D dental restoration model using a dentition scan dataset comprising one or more scan datasets of a real dental abutment preparation site and a corresponding laboratory-generated dental prosthesis. In this manner, the DNN-generated 3D dental restoration model inherently incorporates one or more features of one or more tooth forms of a dental restoration library, which can become part of database 150.

[0111] A computer-implemented method or other process can train a deep neural network, such as those described in FIGS. 10, 16, and 14(a), or other neural networks, to generate a 3D model of a dental restoration using only the laboratory-designed dentition scan data set. In this manner, the DNN-generated 3D dental prosthesis inherently includes one or more features of a dental prosthesis designed by a human technician using a library template. In some embodiments, the computer-implemented method or other process can train the deep neural network to output a probability vector including probabilities of the occlusal surface of the laboratory-generated dental prosthesis representing the occlusal surface of a missing tooth at a preparation site or margin. Furthermore, the computer-implemented method or other process can train the deep neural network to generate a complete 3D dental restoration model by mapping the occlusal surface and margin line data with the highest probability from the scanned dentition data to the preparation site. Additionally, the computer-implemented method or other process can train a deep neural network to generate side walls of a 3D dental restoration model by mapping the side wall data of a technician-generated dental prosthesis to a probability vector containing the probability that one of the side walls matches the occlusal surface and margin line data from the abutment preparation site.

[0112] 15 , at 1215, dentition scan data (e.g., scanned dental impression, physical model, or intraoral scan) of the new patient is received and imported to generate a new 3D model of the dental prosthesis for the new patient. In some embodiments, the new patient's dentition scan data may be pre-processed to convert the 3D image data into 2D image data, making the dentition scan data more amenable to ingestion by a specific neural network algorithm. At 1220, one or more dental features are identified in the new patient's dentition scan data using a previously trained deep neural network. The identified features may be, for example, the abutment preparation site, the corresponding margin line, adjacent teeth and corresponding features, and the surrounding gingiva.

[0113] At 1225, a complete 3D dental restoration model may be generated using the trained deep neural network based on the features identified at 1220. In some embodiments, the trained deep neural network may be tasked with generating a complete 3D dental restoration model by generating an occlusion of the dental prosthesis relative to the abutment preparation site, obtaining margin line data from the generated margin proposal as described above or from the patient's dentition scan data, optionally optimizing the margin line, and generating sidewalls between the generated occlusion and the margin line. Generating the occlusion may include generating an occlusion surface having one or more of a mesio-buccal cusp, a buccal groove, a distal-buccal cusp, a distal-buccal groove, a distal pit, a lingual groove, a mesio-lingual cusp, etc.

[0114] In some embodiments, the trained deep neural network can obtain margin line data from generated margin proposals as described above or from the patient's dentition scan data. In some embodiments, the trained deep neural network can optionally be modified by comparing and mapping the contour of the obtained margin line with thousands of other similar margin lines (e.g., margin lines at the same abutment preparation site) with similar adjacent teeth, surrounding gingiva, etc.

[0115] To generate a complete 3D model, the trained deep neural network can generate sidewalls to fit between the generated occlusion surface and the margin line. This can be done by mapping the sidewalls of thousands of laboratory-generated dental prostheses to the generated occlusion and margin line. In some embodiments, the sidewall with the highest probability value (in the probability vector) can be selected as the base model from which the final sidewalls between the occlusion surface and the margin line will be generated.

[0116] FIG. 16 illustrates example inputs and outputs of a trained deep neural network 1300 (e.g., a GAN) according to some embodiments of the present disclosure. As shown, an input dataset 1305 may include a new patient's dentition having an abutment preparation site 1310. Using the trained one or more deep neural networks 1300, the dental restoration server can generate a (DNN-generated) 3D model of a dental restoration 1315. The DNN-generated dental prosthesis 1315 includes an occlusal portion 1320, a margin line portion 1325, and a sidewall portion 1330. In some embodiments, the deep neural network can generate sidewalls for the prosthesis 1315 by analyzing thousands of technician-generated dental prostheses—generated based on one or more library templates—and mapping them to the abutment preparation site 1310. Finally, the sidewall with the highest probability value can be selected as the model to generate the sidewall 1330.

[0117] FIG. 17(a) is a high-level block diagram illustrating the structure of a generative adversarial network (GAN network) that can be employed to identify and model dental anatomical features and restorations, according to some embodiments of the present disclosure. At a high level, the GAN network employs two independent neural networks against each other to generate output models that are substantially indistinguishable when compared to real models. In other words, the GAN network employs a maximum optimization problem to obtain convergence between two competing neural networks. The GAN network includes a generator neural network 1410 and a discriminator neural network 1420. In some embodiments, both the neural network 1410 and the discriminator neural network 1420 are deep neural networks structured to perform unstructured and unsupervised learning. In a GAN network, both the generator network 1410 and the discriminator network (discriminative deep neural network) 1420 are trained simultaneously. The generator network 1410 is trained to generate samples 1415 from data input 1405. The classifier network 1420 is trained to provide the probability that a sample 1415 belongs to a training data sample 1430 (a real sample, resulting from real data 1425) rather than one of the data samples in the input 1405. The generator network 1410 is recursively trained to maximize the probability that the classifier network 1420 becomes indistinguishable (at 1435) between the training data set and the output samples generated by the generator 1410.

[0118] At each iteration, the classifier network 1420 may output a loss function 1440 that is used to quantify whether the generated sample 1415 is a real natural image or one generated by the generator 1410. The loss function 1440 may be used to provide the feedback necessary for the generator 1410 to improve each successive sample generated in subsequent cycles. In some embodiments, the generator 1410 may vary one or more of the weighting and / or bias variables to generate other outputs depending on the loss function.

[0119] In some embodiments, a computer-implemented method or other process may simultaneously train two adversarial networks, a generator 1410 and a classifier 1420. The computer-implemented method or other process may train the generator 1410 to generate sample models of one or more dental features and / or restorations using one or more patient dentition scan datasets. For example, the patient dentition scan datasets may be 3D scan data of a mandible including prepared teeth / sites and their adjacent teeth. Simultaneously, the computer-implemented method or other process may train the classifier 1420 to distinguish a generative 3D model of a crown for the prepared tooth (generated by the generator 1410) from a sample crown from a real dataset (a collection of multiple scan datasets with crown images). In some embodiments, the GAN network is designed for unsupervised learning, so the input 1405 and the real data 1425 (e.g., a dentition training dataset) do not need to be labeled.

[0120] 17(b) is a flowchart of a method 1450 for generating a 3D model of a dental restoration according to some embodiments of the present disclosure. Method 1450 can be performed by a computer-implemented method or other process on a dental restoration server or one or more other computers in a cloud computing environment. The instructions, processes, and algorithms of method 1450 can be stored in a memory of a computing device and, when executed by a processor, enable the computing device to perform training of one or more deep neural networks to generate the 3D dental prosthesis. Some or all of the processes and procedures described in method 1450 can be performed by one or more other entities or processes within the dental restoration server or other remote computing device. Furthermore, one or more blocks (processes) of method 1450 can be performed in parallel, in a different order, or omitted.

[0121] At 1455, a computer-implemented method or other process may train a generative deep neural network (e.g., GAN generator 1410) to generate a 3D model of a dental prosthesis, such as a crown, using the unlabeled dentition data set. In some embodiments, a labeled and classified dentition data set may be used, but is not required. The generative deep neural network may be implemented by a computer-implemented method or other process within the dental restoration server or outside the dental restoration server, or in a separate and independent neural network.

[0122] At 1460 and substantially simultaneously, the computer-implemented method or other process may also train a discriminative deep neural network (e.g., classifier 1420) to recognize that the dental restoration generated by the generative deep neural network is a model relative to a digital model of a real dental restoration. In the recognition process, the discriminative deep neural network may generate a loss function based on a comparison of the real dental restoration and the generative model of the dental restoration. The loss function provides a feedback mechanism for the generative deep neural network. Using information from the output loss function, the generative deep neural network may generate a better model that may make it easier for the discriminative neural network to mistake the generative model for the real model.

[0123] The generative deep neural network and the discriminative neural network can be considered to be mutually adversarial. In other words, the goal of the generative deep neural network is to generate a model that the discriminative deep neural network cannot distinguish between a model belonging to the real sample distribution and a model belonging to the imitation sample distribution (generative model). If, at 1465, the generative model has a probability value indicating that it is most likely an imitation, training of both deep neural networks is repeated and continued again at 1455 and 1460. This process continues and iterates until the discriminative deep neural network can no longer distinguish between the generative model and the real model. In other words, the probability that the generative model is an imitation is very low, or the probability that the generative model belongs to the real sample distribution is very high.

[0124] Once the deep neural network is trained, the method 1450 can generate a model of the dental restoration based on the patient's dentition dataset received at 1470. At 1475, a model of the patient's dentition dataset is generated using the received patient's dentition dataset.

[0125] In some embodiments, the automated virtual restoration design may include determining an insertion direction of the generated 3D virtual restoration. Steps for automatically determining an insertion direction of the generated 3D virtual restoration can be found in U.S. Patent Application Publication No. 2021 / 030487 to Nikolskiy et al., incorporated herein by reference in its entirety. In some embodiments, the automated virtual restoration design may include pulling the restoration to the margin along the determined insertion path. FIG. 18 shows an example of some embodiments of a virtual crown 802 elevated along the insertion path of a virtual abutment preparation tooth 804. In some embodiments, the elevated crown is movable along the insertion path using a GUI element such as a slider 806 or other equivalent GUI element.

[0126] Some embodiments of the computer-implemented method of automating virtual dental restoration design may include detecting the presence or absence of a problem with a physical abutment preparation during the automated virtual restoration design. In some embodiments, the step of the automated virtual dental restoration design detecting the presence or absence of a problem with a physical abutment preparation during the automated virtual restoration design may be performed while the patient is at the dental office.

[0127] In some embodiments, the problem of the one or more physical preparation teeth may include automatically determining one or more undercut regions of the virtual preparation teeth. One or more examples of automatically determining one or more undercut regions of the virtual preparation teeth can be found in previously incorporated by reference U.S. Patent Application No. 16 / 918,586. As described therein, in some embodiments, automatically determining one or more undercut regions of the virtual preparation teeth may occur during step 418 of automatically determining an insertion direction for the virtual preparation teeth, as shown in FIG.

[0128] As shown in FIG. 19 , in some embodiments, the computer-implemented method can set a default insertion path that is the optimal insertion path that minimizes undercuts 911. FIG. 19 illustrates a cross-sectional view 950 of a portion of a patient's dentition in 2D. It is understood that the patient's dentition is in 3D. In some embodiments, the undercuts may represent one or more sidewall regions extending from the virtual tooth surface. The undercuts 911 may cause one or more virtual preparation tooth lateral regions 958 of the virtual abutment preparation tooth 963 to occlude the margin, for example, when viewed from the insertion path 952 or 956. This may cause restoration seating issues, for example, because the restoration 954 in some embodiments will be placed in maximum contact with the margin. If any portion of the virtual margin is occluded along the insertion path by one or more virtual preparation tooth lateral regions, the computer-implemented method can determine that a virtual open margin exists. In some embodiments, the open margin may include one or more undercut regions occluding the margin along the insertion direction.

[0129] FIG. 20 shows an example of a virtual open margin. FIG. 20 shows an insertion path 1022 with a virtual margin 1026. Due to a virtual abutment preparation tooth lateral area 1028, the virtual abutment preparation tooth has an open virtual margin 1030. In some embodiments, the computer-implemented method can automatically determine a virtual abutment preparation sidewall reduction value 1024 (also referred to as an undercut value). The computer-implemented method can determine this value, for example, by determining how much of the sidewall creates the open virtual margin 1030 when viewed along the insertion path 1022. As shown in FIG. 20 , in some embodiments, the computer-implemented method determines one or more virtual abutment preparation tooth reduction areas as the virtual abutment preparation tooth lateral area 1028 that occludes the virtual margin 1026 when viewed from the insertion point 1022. The computer-implemented method can determine the amount of virtual abutment preparation tooth lateral reduction 1024 required to close the open virtual margin 1030 from the insertion point 1022. In some embodiments, the computer-implemented method can determine one or more virtual abutment preparation tooth lateral regions to reduce to close the margin, hi some embodiments, the virtual abutment preparation tooth lateral regions to reduce are virtual abutment preparation tooth reduction regions.

[0130] In some embodiments, one or more undercut areas may indicate a poor quality physical preparation. In some embodiments, one or more undercut areas that obstruct the insertion path may indicate a poor quality physical preparation, requiring modification of the physical preparation. In some embodiments, one or more undercut areas that create an open margin may indicate a poor quality physical preparation, requiring modification of the physical preparation.

[0131] In some embodiments, the one or more physical preparation tooth issues may include automatically determining gap issues between the virtual antagonist and the virtual restoration. One or more examples of automatically determining gap issues between the virtual antagonist and the virtual restoration can be found in U.S. Patent Application No. 16 / 918,586, previously incorporated by reference herein in its entirety. In some embodiments, determining gap issues may occur in the automated design cement space step 420 shown in FIG. 4. When a restoration is attached to a physical preparation tooth, a minimum gap is required to provide adequate contact with the opposing tooth on the other jaw. In some embodiments, the minimum gap may include a cement space plus a minimum restoration thickness value.

[0132] In some embodiments, a lack of clearance with the virtual antagonist may mean that the physical preparation is of poor quality, necessitating a revision of the physical preparation.

[0133] In some embodiments, problems with one or more physical preparations may include determining that a margin line cannot be automatically generated. In some embodiments, determining that a margin line cannot be automatically generated may occur in the margin AI step 416 of the automated design. In some embodiments, determining that a margin line cannot be automatically generated may be due to an unclear scan for the physical preparation or an unclear physical margin line. In some embodiments, determining that a margin line cannot be automatically generated may be due to an overly smoothed physical margin. In some embodiments, determining that a margin line cannot be automatically generated may be due to a lack of curvature in the physical preparation or physical margin. In some embodiments, the success rate of generating a physical restoration is related to the amount of determinable margin lines. The more determinable margin lines are, the higher the success rate of generating a physical restoration. In some embodiments, the success rate of generating a physical restoration is high if it exceeds a user-configurable threshold. In some embodiments, margin line problems may also occur when the margin extends into an adjacent tooth.

[0134] In some embodiments, determining that a margin line cannot be automatically generated may include a poor quality physical abutment preparation, necessitating modification of the physical margin and / or physical abutment preparation to increase the visibility of the physical margin and / or correct for a margin line extending into an adjacent tooth.

[0135] Some embodiments of the computer-implemented method for automating virtual dental restoration design may include virtually displaying to a dentist or other user problems with one or more physical abutment preparation teeth detected during execution of the automated virtual restoration design. In some embodiments, the virtual dental restoration design automation virtually displaying to a dentist or other user problems with one or more physical abutment preparation teeth detected during execution of the automated virtual restoration design may be performed while the patient is at the dental office, for example, during a patient visit and / or while the patient is in a dental chair undergoing dental treatment. Virtually displaying to a dentist or other user problems with one or more physical abutment preparation teeth may provide guidance and / or feedback to the dentist and / or user regarding the quality of the physical abutment preparation teeth. In some embodiments, virtually displaying to a dentist or other user problems with one or more physical abutment preparation teeth may be performed in near real time. In some embodiments, virtually displaying to a dentist problems with one or more physical abutment preparation teeth may include highlighting one or more areas requiring reduction on the 3D virtual dental model.

[0136] In some embodiments, the computer-implemented method may display the problems on a computer display via a graphical user interface ("GUI"). In some embodiments, virtually displaying problems with one or more physical abutment preparation teeth to the dentist on the display may include providing dentist guidance on the virtual 3D dental model to correct one or more areas of the physical abutment preparation teeth. This may be performed, in some embodiments, while the patient is still seated in the dental chair in the dental office. In some embodiments, the guidance gives the dentist insight into problems caused by their preparation of the physical abutment preparation teeth. In some embodiments, the guidance enables the dentist to learn to reduce the occurrence of future problems caused by their preparation of the physical abutment preparation teeth.

[0137] In some embodiments, virtually displaying problems with one or more physical abutment preparation teeth to the dentist may include displaying on a display one or more marked sidewall regions that result in undercut regions in the virtual abutment preparation teeth in the virtual dental model. As shown in FIG. 21 , in some embodiments, the computer-implemented method may determine one or more virtual abutment preparation tooth reduction regions as virtual abutment preparation tooth lateral regions 1130 that occlude a virtual margin 1126 when viewed from an insertion point 1122. The virtual abutment preparation tooth lateral regions 1130 may indicate problems with the insertion and proper seating of a physical restoration on the physical abutment preparation tooth. The computer-implemented method may determine an amount of virtual abutment preparation tooth lateral reduction 1124 required to close an open virtual margin 1128 from the insertion point 1122. In some embodiments, the computer-implemented method may determine and display one or more virtual abutment preparation tooth lateral regions to reduce to close the margin, along with the amount of reduction required to close the margin. In some embodiments, the computer-implemented method can display to the dentist or other user one or more physical abutment preparation tooth lateral wall regions to be reduced and the amount of reduction. The virtual abutment preparation tooth lateral wall regions to be reduced correspond to the physical abutment preparation tooth reduction regions. Displaying the virtual abutment preparation tooth lateral wall regions to the dentist or other user while the patient is undergoing treatment allows the dentist to fabricate the reductions for the physical abutment preparation teeth while the patient is still in the chair and in the same visit. This can reduce turnaround time by allowing the dentist to address issues with the physical abutment preparation teeth in a single visit, thereby eliminating the need for the patient to return for additional physical abutment preparation tooth reductions to address issues with the physical abutment preparation teeth.

[0138] In some embodiments, virtually displaying problems with one or more physical preparation teeth to the dentist may include displaying one or more marked gap problems for the virtual preparation teeth on a display. In some embodiments, the one or more marked gap problems are detectable during the cement spacing step of the automated design. In some embodiments, the gap problems may relate to thickness of the restoration and gaps between the physical preparation teeth and the physical antagonist.

[0139] 22 , in some embodiments, the computer-implemented method may detect an insufficient virtual occlusal gap 1250 by determining that the virtual occlusal gap 1221 between the occlusal surfaces of one or more virtual abutment preparation teeth and the occlusal surfaces of one or more virtual antagonist teeth is less than the minimum required occlusal gap. In some embodiments, the computer-implemented method may determine the virtual occlusal gap when the virtual jaws are closed or clenched, or when the virtual abutment preparation tooth 1230 and the virtual antagonist tooth 1234 are closest to one another. The computer-implemented method may thus determine that the height of the virtual abutment preparation tooth 1230 and the height of the virtual antagonist tooth 1234 are too large to accommodate the minimum restoration thickness of the restoration therebetween when the jaws are closed or clenched.

[0140] To accommodate a restoration between the virtual preparation tooth 1230 and the virtual antagonist tooth 1234, the computer-implemented method can determine the total virtual reduction required to satisfy the minimum required occlusal gap. The computer-implemented method can display the total virtual reduction in a GUI to indicate the total required reduction. In some embodiments, the total virtual reduction is, for example, the difference between the virtual occlusal gap and the minimum required occlusal gap. In some embodiments, the computer-implemented method can determine a default virtual reduction value. For example, in some embodiments, the insufficient gap can be insufficient occlusal gap 1250 between the occlusal surface of the virtual preparation tooth 1230 and the occlusal surface of the virtual antagonist tooth 1234.

[0141] In some embodiments, the physical abutment preparation tooth may be modified by a dentist to address one or more issues with the physical abutment preparation tooth. Some embodiments may include having the dentist modify the physical abutment preparation tooth (and / or opposing or surrounding teeth / dentition), rescanning at least a portion of the patient's dentition including the modified physical abutment preparation tooth and / or opposing teeth and / or surrounding dentition to generate a modified 3D virtual dental model including the modified virtual abutment preparation tooth and / or opposing teeth and / or surrounding dentition, and uploading the modified 3D virtual dental model. In some embodiments, the modified 3D virtual dental model is used for the same case without creating a new case.

[0142] Once the dentist has made any necessary modifications to the physical preparation / antagonist / surrounding dentition, the computer-implemented method may further include receiving a modified 3D virtual dental model including at least one modified virtual preparation and / or at least one modified virtual antagonist and / or modified dentition, which in some embodiments includes a virtual representation of the modified physical preparation modified by the dentist. In some embodiments, the dentist's modifications, rescanning, and re-uploading are performed while the patient is seated in the dental chair receiving treatment.

[0143] Some embodiments of the computer-implemented method of automating virtual dental restoration design may include virtually displaying the generated virtual restoration to a dentist or other user for one or more adjustments if no issues with the physically prepared tooth are detected while running the automated virtual restoration design. In some embodiments, the step of virtually displaying the generated virtual restoration to a dentist or other user for one or more adjustments if no issues with the physically prepared tooth are detected while running the automated virtual restoration design may be performed while the patient is at the dental office.

[0144] In some embodiments, the one or more adjustments may include adjusting a virtual margin line. In some embodiments, the one or more adjustments may include adjusting virtual contacts with an opposing tooth. In some embodiments, the one or more adjustments may include adjusting virtual contacts with one or more teeth adjacent to the abutment preparation tooth. In some embodiments, the adjustments may include adjustments to the margin line or adjustments to the virtual restoration. Adjustments are also referred to as "design confirmation" or "DC."

[0145] Some embodiments may include performing adjustments, i.e., DC, on the generated 3D virtual dental restoration model. In some embodiments, the computer-implemented method may display at least a portion of the 3D virtual model of the patient's dentition, including the generated 3D virtual dental restoration model, on a display, such as a computer screen, in a graphical user interface ("GUI") that may include interaction controls that allow a dental technician, dentist, or other user to manipulate one or more features of the generated 3D virtual dental restoration model.

[0146] FIG. 23( a) shows an example of a GUI 1350 that may be used as part of a DC process in some embodiments. In this example, a generated 3D virtual restoration model is loaded for DC. The DC process may display at least a portion of the 3D virtual dental model 1352 of the patient's dentition as well as the generated 3D virtual dental restoration model 1354 in GUI 1350, along with information regarding the 3D virtual dental restoration model 1354 and its position and orientation relative to the surrounding dentition. For example, in some embodiments, a computer-implemented method may display and indicate the virtual tooth number 1356 along with its adjacent virtual teeth in a representation of the upper or lower jaw. In some embodiments, the DC process may display information regarding the virtual tooth 1354 and its adjacent virtual teeth in a panel, such as panel 1358 or other suitable GUI display element known in the art. Panel 1358 may provide information regarding, for example, the occlusal, mesial, and distal relationship of the generated 3D virtual dental restoration model to the surrounding dentition. The GUI 1350, in some embodiments, may provide one or more control features for adjusting the 3D virtual dental restoration model 1354. For example, in some embodiments, the DC process may provide controls to adjust the contact points that the automatically generated 3D virtual dental restoration has with respect to adjacent virtual teeth in the 3D virtual dental model.

[0147] In some embodiments, the DC process may provide GUI controls for adjusting contact points, such as mesial, distal, and / or occlusal contact points. The mesial and distal contact points may be between the generated 3D virtual dental restoration model and an adjacent virtual tooth in the 3D virtual dental model. The occlusal contact points may be between the occlusal surface of the generated 3D virtual dental restoration model and an opposing virtual tooth on an opposing virtual jaw. FIG. 23(b) illustrates an example of the steps for adjusting mesial contact points in some embodiments. As shown in the figure, the GUI 1360 may display at least a portion of the 3D virtual dental model along with the mesial side of the generated 3D virtual dental restoration model 1362. The GUI 1360 may display a mesial contact surface area 1364 between the 3D virtual dental restoration model 1362 and its mesial adjacent tooth (not shown) in the 3D virtual dental model. The GUI 1360 may provide an adjustment tool that allows a user to select, using an input device, a mesial adjustment surface area 1366 that the computer-implemented method can adjust, for example. In some embodiments, the adjustment may decrease the size of a conditioning surface area, such as conditioning surface area 1366. In some embodiments, the adjustment may increase the size of conditioning surface area 1366. FIG. 23( c) illustrates an example of adjusting a distal contact point in some embodiments. As shown in the figure, a GUI 1370 may display at least a portion of a 3D virtual dental model along with a distal side of a generated 3D virtual dental restoration model 1372. The GUI 1370 may display a distal contact surface area 1374 between the 3D virtual dental restoration model 1372 and its distal neighbor (not shown) within the 3D virtual dental model. The GUI 1370 may provide an adjustment tool that allows a user to select, using an input device, a distal conditioning surface area 1376 that the computer-implemented method may adjust, for example. In some embodiments, the adjustment may decrease the size of a conditioning surface area, such as conditioning surface area 1376. In some embodiments, the adjustment may increase the size of conditioning surface area 1376.

[0148] In some embodiments, the DC process may provide GUI controls that allow the user to adjust the occlusal contact points. For example, Figure 23(d) shows a generated 3D virtual dental restoration model 1380 viewed from the occlusal direction, showing occlusal surfaces, such as occlusal surface 1382. In some embodiments, the computer-implemented method may provide one or more virtual tools for adjusting occlusal contact areas, such as occlusal contact area 1384. In some embodiments, the adjustment may decrease the size of the adjustment surface area, such as occlusal contact area 1384. In some embodiments, the adjustment may increase the size of the adjustment surface area 1384.

[0149] In some embodiments, the DC process may provide GUI controls that allow a user to adjust the shape or contour of the automatically generated 3D virtual dental restoration, for example, as shown in FIGS. 23(e) and 23(f). In the example of FIG. 23(e), the user may select a contour region, such as contour region 1385, to adjust. In the example of FIG. 23(f), the user may select a contour region, such as contour region 1387. In some embodiments, the contour control may include a visual indicator that may define the contour region. An example of such a visual indicator may include an "X" or hash mark, the size of which may be adjusted by the user. An example of such a visual indicator is visual indicator 1386. Upon hovering a pointer over the generated 3D virtual dental restoration, in some embodiments, a visual indicator may appear on at least a portion of the generated 3D virtual dental restoration model. In some embodiments, the user may adjust the shape or contour of the contour region, for example, by pressing a button on an input device, such as a mouse, and dragging the contour region in a desired direction. In some embodiments, other GUI controls known in the art may be used to allow the user to adjust the shape or contour of the automatically generated 3D virtual dental restoration.

[0150] In some embodiments, the DC process displays at least a portion of a 3D virtual dental model 1388 of the patient's dentition and the proposed automatically determined margin line, and allows the user to modify the determined margin line. Figure 23(g) shows an example of the DC process displaying the proposed determined margin line 1389 in a GUI. In some embodiments, the 3D virtual dental restoration is hidden or not displayed so that the determined margin line is visible. In some embodiments, the GUI can provide virtual handles 1390 to allow the user to adjust the automatically determined margin line. This advantageously allows, for example, correction of the automatically determined margin line as part of the DC process.

[0151] In some embodiments, once changes to the generated 3D virtual dental restoration model as part of the DC process are completed, the computer-implemented method may apply the changes to the 3D virtual dental restoration model to provide a modified 3D virtual dental restoration model. In some embodiments, the changes are made to provide visual feedback. In some embodiments, where changes to the model are significant or fundamental, the computer-implemented method may regenerate the 3D virtual dental restoration using a generative neural network. In some embodiments, significant and / or fundamental changes may include, for example, but are not limited to, changes to the proposed margin line. In some embodiments, significant and / or fundamental changes may be based on user-configurable change values, for example, as measured geometrically within the model. In some embodiments, the computer-implemented method may perform one or more features described herein on the regenerated 3D virtual dental restoration model to provide a regenerated 3D virtual dental restoration model for the DC process. In some embodiments, where changes to the DC are not significant or fundamental, the computer-implemented method may apply changes to the virtual margin line and the generated 3D virtual dental restoration model without regeneration. For example, in some embodiments, the computer-implemented method may include, upon receiving a minor adjustment to the margin line, adjusting the virtual margin line and / or the virtual restoration as needed. In some embodiments, the computer-implemented method may include, upon receiving a minor adjustment to the virtual restoration, applying the minor adjustment to the virtual restoration without regenerating the virtual restoration. In some embodiments, the computer-implemented method may include determining issues with one or more physical abutment preparation teeth in the regenerated virtual restoration. In some embodiments, any adjustments can be made by a dentist in the dental office while the patient is seated during treatment.

[0152] Some embodiments may include tracking a dentist's performance based on the quality of one or more physical abutment preparations. Some embodiments may include tracking a dentist's performance based on the quality of one or more physical abutment preparations. Some embodiments may include tracking the performance of a dental clinic, including one or more dentists, based on the quality of one or more physical abutment preparations prepared at the dental clinic by one or more dentists. In some embodiments, the tracking step includes analyzing dentists and dental clinics and their performance over a predetermined period of time. In some embodiments, the analysis includes one or more of the following: order ID, tooth ID, patient ID, patient name, doctor name, comments, location of milling / fabrication, type of restoration, material, source of scan file (scanner, computer, or saved scan), and guidance information. In some embodiments, the guidance information includes the number of scanning sessions (rescans) performed, the duration of the scans, the type of problem found in each scan, and the solution obtained for each scan (how it was solved). In some embodiments, the scan data is recorded and not overwritten during rescans. Some embodiments may include establishing a baseline level of performance. In some embodiments, the baseline level of performance includes the number of physical preparations that cause problems. Some embodiments may include curating educational content based on the types of problems commonly encountered when preparing preparation teeth.

[0153] In some embodiments, the obtained analysis and guidance information can be provided as aggregated feedback to dentists, clinicians, and practices. In some embodiments, the analysis, guidance, and other information can be provided to show trends over time. In some embodiments, providing this very short, closed feedback loop can advantageously improve the preparation over time. The analysis, guidance, and information, along with the aggregated feedback, can provide progress reports and can help the DSO work with dentists and practices that need to improve to meet internal performance metrics.

[0154] Some embodiments may include providing individual dentists with feedback regarding their particular abutment preparation techniques to minimize future abutment preparation problems. Some embodiments may incorporate educational content into continuing education programs for dentists. In some embodiments, the performance comprises a scorecard. In some embodiments, a scorecard with guidance information is displayed after each treatment session. In some embodiments, a dashboard may show application usage and overall performance. In some embodiments, the scorecard may show success / failure rates over a period of time. In some embodiments, the scorecard may provide success / failure rates for one or more other dentists. In some embodiments, the one or more other dentists are within the same dental practice. In some embodiments, the dental practice may include a DSO. Some embodiments may include providing a summary of the scorecard to the DSO. This may help the DSO identify areas where the dentist may need more training or guidance, and may also be used to determine the performance of individual dentists, for example.

[0155] Some embodiments may include milling a physical 3D virtual restoration from the successfully generated 3D virtual restoration. In some embodiments, the manufacturing facility may be a dental laboratory. In some embodiments, the manufacturing facility performs manufacturing validation. In some embodiments, the dental laboratory or other manufacturing facility is located outside the dental office.

[0156] In some embodiments, the milling may be a computer-aided manufacturing process ("CAM"). Some embodiments may include staging the one or more physical restorations. In some embodiments, staging may include grouping the one or more physical restorations by patient for shipment. Some embodiments may include bundling the one or more physical restorations. In some embodiments, bundling may include grouping the one or more restorations together for a dental office for bulk shipment to the dental office.

[0157] Some embodiments may include routing the virtual 3D virtual restoration model to a computer-aided manufacturing ("CAM") process. In some embodiments, the CAM process may be performing a design machinability check. In some embodiments, the design machinability check may include the following steps, not necessarily in this order: (1) generating a virtual milled restoration from the NC file (milling strategy). In some embodiments, the result of this staging may be milled surfaces that should match the actual milled crown. In some embodiments, the virtually milled restoration does not include one or more undercuts. (2) comparing the virtually milled restoration with the virtual restoration design. In some embodiments, the comparing step may be comparing the lateral and medial surfaces of the virtually milled restoration and the bite table. In some embodiments, if there are differences between the virtually milled restoration and the virtual restoration design, the design machinability check fails. In some embodiments, if the design machinability check fails, the virtual restoration is routed for manual milling. In some embodiments, the automatic milling check passes if there are no differences between the virtually milled restoration and the virtual restoration design. In some embodiments, if the automatic milling check passes, the virtual restoration is routed for automatic milling. In some embodiments, automatic milling comprises the following steps: (a) nesting, (b) identifying occlusions based on magnification and shading, (c) milling the restoration (e.g., crown, etc.), (d) determining staining / shading (gingival and occlusal), and (e) sintering the restoration.

[0158] In some embodiments, a machinability failure may be an undercut that cannot be milled, a restoration size that is too large for occlusion, or unusable shading. In some embodiments, if the machinability check fails, the virtual restoration design is routed to manual machining. In some embodiments, if the machinability check passes, the virtual design restoration is routed to automated machining. In some embodiments, if the design machinability check passes, the CAM process routes the virtual 3D virtual restoration model to automated milling to perform automated milling. In some embodiments, once automated milling is complete, a virtual milling DC is performed. In some embodiments, if the virtual milling DC passes, staging is performed.

[0159] One or more advantages of one or more features may include, for example, overall time savings, reduced chairside time, and an improved patient experience by avoiding multiple treatment return visits. One or more advantages of one or more features may include, for example, reducing or eliminating discarded physical restorations due to one or more issues such as gaps, insets, and / or undercuts. One or more advantages of one or more features may include, for example, improved quality of physical restorations. One or more advantages of one or more features may include, for example, a reduction in the number of re-creations of physical restorations. One or more advantages of one or more features may include, for example, a reduction in the number of patient visits to a dental or other user's office and a reduction in the number of times a patient undergoes anesthesia. One or more advantages of one or more features may include, for example, providing a dentist with near real-time feedback regarding a physical abutment tooth to enable corrections while treating a patient chairside. One or more advantages of one or more features may include, for example, allowing a dentist to prepare a tooth and generate a virtual restoration for that tooth in a single visit. One or more advantages of one or more features may include, for example, improved (faster) turnaround time to obtain a physical restoration. One or more advantages of one or more features may include, for example, reduced patient chair time. One or more advantages may include, for example, reduced restoration rejection due to one or more problems, optionally including, but not limited to, undercut problems, gap problems, and / or open margin problems.

[0160] Some embodiments include a processing system for automating virtual dental restoration design, the processing system including a processor and a computer-readable storage medium including instructions executable by the processor to perform the following steps: receiving a 3D virtual dental model of at least a portion of a patient's dentition, the 3D virtual dental model comprising at least one virtual abutment preparation tooth, the virtual abutment preparation tooth comprising a digital representation of a physical abutment preparation tooth prepared by a dentist; performing automated virtual restoration design using the 3D virtual dental model; virtually displaying to the dentist any problems with the one or more physical abutment preparation teeth detected during performing the automated virtual restoration design; and, if no problems with the physical abutment preparation teeth are detected during performing the automated virtual restoration design, virtually displaying the generated virtual restoration to the dentist for one or more adjustments.

[0161] 24 is a flowchart illustrating one or more steps in some embodiments, which may include, at 1402, receiving a 3D virtual dental model of at least a portion of a patient's dentition, the 3D virtual dental model comprising at least one virtual abutment preparation tooth, the virtual abutment preparation tooth comprising a digital representation of a physical abutment preparation tooth prepared by a dentist, at 1404, performing automated virtual restoration design using the 3D virtual dental model, at 1406, virtually displaying to the dentist any problems with the one or more physical abutment preparation teeth detected during the performing of the automated virtual restoration design, and, if no problems with the physical abutment preparation teeth were detected during the performing of the automated virtual restoration design, at 1408, virtually displaying the generated virtual restoration to the dentist for one or more adjustments.

[0162] 25 illustrates a processing system 14000 in some embodiments. The system 14000 may include a processor 14030 and a computer-readable storage medium 14034 having instructions executable by the processor to perform one or more steps described in this disclosure. In some embodiments, for example, one or more features may be performed by a user using an input device while viewing a virtual model on a display. In some embodiments, the computer-implemented method may enable the input device to manipulate the virtual model displayed on the display. For example, in some embodiments, the computer-implemented method may enable the input device to rotate, zoom, move, and / or manipulate the virtual model in any manner known in the art.

[0163] In some embodiments, one or more virtual surfaces of the 3D virtual model may be selected over the virtual teeth or other regions, for example, using an input device whose pointer is indicated on the display. The pointer may be used to select a single area by, for example, clicking an input device such as a mouse or tapping a touch panel. In some embodiments, multiple virtual surfaces may be selected, for example, by dragging the pointer across the virtual surface. Points or virtual surfaces may be selected using other techniques known in the art.

[0164] In some embodiments, the computer-implemented method may, for example, display the virtual model on a display and receive input from an input device, such as a mouse or touch panel, on the display. Upon receiving the manipulation command, the computer-implemented method may, in some embodiments, rotate, zoom, move, and / or manipulate the virtual model in any manner known in the art.

[0165] One or more of the features disclosed herein may be performed and / or achieved automatically without manual or user intervention. One or more of the features disclosed herein may be performed by a computer-implemented method. The disclosed features (including, but not limited to, methods and systems) may be implemented in a computing system. For example, the computing environment 14042 used to perform these functions may be any of a variety of computing devices (e.g., desktop computers, laptop computers, server computers, tablet computers, gaming systems, mobile devices, programmable automation controllers, video cards, etc.) that may be incorporated into a computing system comprising one or more computing devices. In some embodiments, the computing system may be a cloud-based computing system.

[0166] For example, the computing environment 14042 may include one or more processing units 14030 and memory 14032. The processing unit executes computer-executable instructions. The processing unit 14030 may be a central processing unit (CPU), a processor in an application-specific integrated circuit (ASIC), or any other type of processor. In some embodiments, the one or more processing units 14030 may, for example, execute multiple computer-executable instructions in parallel. In a multi-processing system, multiple processing units execute computer-executable instructions to increase processing power. For example, a typical computing environment may include a central processing unit as well as a graphics processing unit or co-processing unit. The tangible memory 14032 may be volatile memory accessible by the processing unit (e.g., registers, cache, RAM), non-volatile memory (e.g., ROM, EEPROM, flash memory, etc.), or some combination of the two. The memory stores software implementing one or more of the innovations described herein in the form of computer-executable instructions suitable for execution by the processing unit.

[0167] A computing system may have additional features. For example, in some embodiments, a computing environment includes storage 14034, one or more input devices 14036, one or more output devices 14038, and one or more communication connections 14037. An interconnection mechanism, such as a bus, controller, or network, interconnects the components of the computing environment. Typically, operating system software provides an operating environment for other software executing in the computing environment and coordinates the activities of the components of the computing environment.

[0168] Tangible storage 14034 may be removable or non-removable and includes magnetic or optical media such as magnetic disks, magnetic tapes or cassettes, CD-ROMs, DVDs, or other media that can be used to store information in a non-transitory manner and that can be accessed within a computing environment. Storage 14034 stores instructions for software that implements one or more of the innovations described herein.

[0169] An input device may be, for example, a keyboard, a mouse, a touch input device such as a pen or trackball, an audio input device, a scanning device, any of a variety of sensors, or other device or combination thereof that provides input to the computing environment. For video coding, an input device may be a camera, a video card, a TV tuner card, or similar device that accepts video input in analog or digital form, or a CD-ROM or CD-RW that reads video samples into the computing environment. An output device may be a display, a printer, speakers, a CD writer, or other device that provides output from the computing environment.

[0170] A communications connection enables communication over a communications medium to another computing entity. The communications medium conveys information such as computer-executable instructions, audio or video input or output, or other data in a modulated data signal. A modulated data signal is a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communications media may use electrical, optical, RF, or other carrier waves.

[0171] Any of the disclosed methods can be implemented as computer-executable instructions stored on one or more computer-readable storage media 14034 (e.g., one or more optical media disks, a volatile memory component (such as DRAM or SRAM) or a non-volatile memory component (such as flash memory or a hard drive)) and executed (e.g., the computer-executable instructions cause one or more processors of a computer system to perform the method) on a computer (e.g., a smartphone, other mobile device including computing hardware, or any commercially available computer including a programmable automation controller). The term computer-readable storage medium does not include communication connections such as signals and carrier waves. Any of the computer-executable instructions for implementing the disclosed technology, as well as any data created and used during the implementation of the disclosed embodiments, can be stored on one or more computer-readable storage media 14034. The computer-executable instructions can be, for example, part of a dedicated software application or a software application accessed or downloaded via a web browser or other software application (e.g., a remote computing application). Such software may be executed, for example, on a single local computer (e.g., any suitable commercially available computer) or in a networked environment using one or more networked computers (e.g., via the Internet, a wide area network, a local area network, a client-server network (such as a cloud computing network), or other similar network).

[0172] For clarity, only selected aspects of a software-based implementation are described. Other details well known in the art are omitted. For example, it should be understood that the disclosed technology is not limited to any particular computer language or program. For example, the disclosed technology may be implemented by software written in C++, Java, Perl, Python, JavaScript, Adobe Flash, or any other suitable programming language. Likewise, the disclosed technology is not limited to any particular computer or hardware type. Specific details of suitable computers and hardware are well known and need not be described in detail in this disclosure.

[0173] It should also be understood that any functionality described herein may be performed at least in part by one or more hardware logic components rather than software. For example, and without limitation, exemplary types of hardware logic components that may be used include Field-Programmable Gate Arrays (FPGAs), Program-Specific Integrated Circuits (ASICs), Program-Specific Standard Products (ASSPs), System-on-a-Chip Systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0174] Additionally, any of the software-based embodiments (e.g., comprising computer-executable instructions for causing a computer to perform any of the disclosed methods) can be uploaded, downloaded, or remotely accessed via appropriate communications means, including, for example, the Internet, the World Wide Web, an intranet, a software application, cable (including fiber optic cable), magnetic communications, electromagnetic communications (including RF, microwave, and infrared communications), electronic communications, or other similar communications means.

[0175] In view of the numerous possible embodiments to which the principles of the present disclosure may be applied, it should be recognized that the described embodiments are merely examples and should not be construed as limiting the scope of the present disclosure.

Claims

1. 1. A computer-implemented method for automating virtual dental restoration design, comprising: receiving a 3D virtual dental model of at least a portion of the patient's dentition, the 3D virtual dental model comprising at least one virtual abutment preparation tooth, the virtual abutment preparation tooth comprising a digital representation of a physical abutment preparation tooth prepared by a dentist; performing automated virtual restoration design using the 3D virtual dental model; virtually displaying to the dentist any problems with one or more physical abutment teeth that are detected during the execution of the automated virtual restoration design; If no problems with the physical abutment tooth are detected during the execution of the automated virtual restoration design, virtually displaying the generated virtual restoration to the dentist for one or more adjustments; A method for providing the above.

2. 2. The method of claim 1, wherein the automated virtual restoration design comprises one or more selected from the group consisting of decimating the 3D virtual dental model, meshing, segmenting, determining an occlusal orientation, determining a bite, localizing a preparation mold, determining a buccal orientation, determining a margin for the at least one virtual preparation tooth, determining an insertion orientation for the virtual preparation tooth, determining a cement space for the virtual preparation tooth, generating the virtual restoration, and tensioning the virtual restoration to the margin.

3. The method of claim 1 , wherein the one or more physical abutment preparation defects include one or more undercut areas.

4. The method of claim 1 , wherein the one or more physical abutment preparation problems include a lack of clearance.

5. The method of claim 1 , wherein the problem with the one or more physical abutment preparation teeth includes a lack of insertion direction.

6. The method of claim 1 , wherein the problem with the one or more physical abutment preparation teeth includes a margin line that cannot be automatically generated.

7. 10. The method of claim 1, wherein displaying problems with the one or more physical abutment preparation teeth comprises highlighting one or more areas requiring reduction on the 3D virtual dental model.

8. The method of claim 1 , further comprising the step of indicating an insertion direction to the dentist upon successful automated design.

9. The method of claim 1 , wherein one or more steps are performed during a single patient visit.

10. 10. The method of claim 9, wherein the patient is seated in a dental chair receiving dental treatment.

11. 10. The method of claim 1, further comprising the steps of: upon detecting one or more issues during automated design, allowing a dentist to modify the physical abutment preparation teeth, re-scanning at least a portion of the patient's dentition with the modified physical abutment preparation teeth to generate a modified 3D virtual dental model with the modified virtual abutment preparation teeth, and uploading the modified 3D virtual dental model.

12. The method of claim 1 , wherein the generated virtual restoration is adjustable by the dentist.

13. The method of claim 1 , further comprising determining a quality of the one or more physical abutment preparations based on the automated design process.

14. 14. The method of claim 13, wherein the automated design error indicates a lower quality physical abutment preparation.

15. 10. The method of claim 1, further comprising tracking the dentist's performance based on the quality of one or more physical abutment preparations.

16. 10. The method of claim 1, further comprising routing the 3D virtual restoration to a computer-aided manufacturing ("CAM") process, the CAM process comprising performing a design machinability check for automated milling.

17. The method of claim 16, further comprising milling the virtual restoration.

18. 1. A non-transitory computer readable medium storing executable computer program instructions for providing virtual dental restoration design automation, the computer program instructions comprising: receiving a 3D virtual dental model of at least a portion of the patient's dentition, the 3D virtual dental model comprising at least one virtual abutment preparation tooth, the virtual abutment preparation tooth comprising a digital representation of a physical abutment preparation tooth prepared by a dentist; performing automated virtual restoration design using the 3D virtual dental model; virtually displaying to the dentist any problems with one or more physical abutment teeth that are detected during the automated virtual restoration design; and and virtually displaying the generated virtual restoration to the dentist for one or more adjustments if no problems with the physical abutment tooth are detected during the execution of the automated virtual restoration design. A medium comprising instructions for:

19. 20. The medium of claim 18, wherein the automated virtual restoration design comprises one or more selected from the group consisting of decimating the 3D virtual dental model, meshing, segmenting, determining an occlusal orientation, determining a bite, localizing a preparation mold, determining a buccal orientation, determining a margin for the at least one virtual preparation tooth, determining an insertion orientation for the virtual preparation tooth, determining a cement space for the virtual preparation tooth, generating the virtual restoration, and tensioning the virtual restoration to the margin.

20. 20. The medium of claim 18, wherein the one or more physical abutment formation tooth defects include one or more undercut areas.

21. 20. The medium of claim 18, wherein the one or more physical abutment preparation tooth problems include a lack of clearance.

22. 20. The medium of claim 18, wherein the problem with the one or more physical abutment preparation teeth comprises a lack of insertion direction.

23. 20. The medium of claim 18, wherein the problem with the one or more physical abutment preparation teeth includes a margin line that cannot be automatically generated.

24. 20. The medium of claim 18, wherein displaying issues with the one or more physical abutment preparation teeth comprises highlighting one or more areas requiring repositioning on the 3D virtual dental model.

25. 20. The medium of claim 18, wherein the computer program instructions further comprise instructions for indicating an insertion direction to the dentist upon successful automated design.

26. 20. The medium of claim 18, wherein one or more steps are performed during a single patient visit.

27. 27. The medium of claim 26, wherein the patient is seated in a dental chair receiving dental treatment.

28. 20. The medium of claim 18, wherein the computer program instructions further comprise instructions for: upon detecting one or more issues during automated design, allowing a dentist to modify the physical abutment preparation teeth, re-scanning at least a portion of the patient's dentition with the modified physical abutment preparation teeth, generating a modified 3D virtual dental model with the modified virtual abutment preparation teeth, and uploading the modified 3D virtual dental model.

29. The medium of claim 18 , wherein the generated virtual restoration is adjustable by the dentist.

30. 20. The medium of claim 18, wherein the computer program instructions further comprise instructions for determining a quality of the one or more physical abutment preparations based on the automated design process.

31. 31. The medium of claim 30, wherein the automated design error indicates a lower quality physical abutment preparation.

32. 20. The medium of claim 18, wherein the computer program instructions further comprise instructions for tracking the dentist's performance based on the quality of one or more physical abutment preparations.

33. 20. The medium of claim 18, wherein the computer program instructions further comprise instructions for routing the 3D virtual restoration to a computer-aided manufacturing ("CAM") process, the CAM process comprising performing a design machinability check for automated milling.

34. 34. The medium of claim 33, wherein the computer program instructions further comprise instructions for milling the virtual restoration.

35. 1. A system for automating virtual dental restoration design, comprising: a processor; 1. A non-transitory computer-readable storage medium, comprising: receiving a 3D virtual dental model of at least a portion of the patient's dentition, the 3D virtual dental model comprising at least one virtual abutment preparation tooth, the virtual abutment preparation tooth comprising a digital representation of a physical abutment preparation tooth prepared by a dentist; performing automated virtual restoration design using the 3D virtual dental model; virtually displaying to the dentist any problems with one or more physical abutment teeth that are detected during the execution of the automated virtual restoration design; If no problems with the physical abutment tooth are detected during the execution of the automated virtual restoration design, virtually displaying the generated virtual restoration to the dentist for one or more adjustments; a non-transitory computer-readable storage medium comprising instructions executable by the processor to perform steps comprising: A system comprising:

36. 36. The system of claim 35, wherein the automated virtual restoration design comprises one or more selected from the group consisting of decimating the 3D virtual dental model, meshing, segmenting, determining an occlusal orientation, determining a bite, localizing a preparation mold, determining a buccal orientation, determining a margin for the at least one virtual preparation tooth, determining an insertion orientation for the virtual preparation tooth, determining a cement space for the virtual preparation tooth, generating the virtual restoration, and tensioning the virtual restoration to the margin.

37. 36. The system of claim 35, wherein the one or more physical abutment preparation tooth defects include one or more undercut areas.

38. 36. The system of claim 35, wherein the problem with the one or more physical abutment preparation teeth comprises a lack of clearance.

39. 36. The system of claim 35, wherein the problem with the one or more physical abutment preparation teeth comprises a lack of insertion direction.

40. 36. The system of claim 35, wherein the problem with the one or more physical abutment preparation teeth includes a margin line that cannot be automatically generated.

41. 36. The system of claim 35, wherein displaying issues with the one or more physical abutment preparation teeth comprises highlighting one or more areas requiring reduction on the 3D virtual dental model.

42. 36. The system of claim 35, wherein the steps performed by the processor further comprise the step of indicating an insertion direction to the dentist upon successful automated design.

43. 36. The system of claim 35, wherein one or more steps are performed during a single patient visit.

44. 44. The system of claim 43, wherein the patient is seated in a dental chair receiving dental treatment.

45. 36. The system of claim 35, wherein the steps performed by the processor further comprise: upon detecting one or more issues during automated design, allowing a dentist to modify the physical abutment preparation tooth, re-scanning at least a portion of the patient's dentition with the modified physical abutment preparation tooth, generating a modified 3D virtual dental model with the modified virtual abutment preparation tooth, and uploading the modified 3D virtual dental model.

46. 36. The system of claim 35, wherein the generated virtual restoration is adjustable by the dentist.

47. 36. The system of claim 35, wherein the steps performed by the processor further comprise determining a quality of the one or more physical abutment preparations based on the automated design process.

48. 48. The system of claim 47, wherein the automated design error indicates a lower quality physical abutment preparation.

49. 36. The system of claim 35, wherein the steps performed by the processor further comprise tracking the dentist's performance based on the quality of one or more physical abutment preparations.

50. 36. The system of claim 35, wherein the steps performed by the processor further comprise routing the 3D virtual restoration to a computer-aided manufacturing ("CAM") process, the CAM process comprising performing a design machinability check for automated milling.

51. 51. The system of claim 50, wherein the steps performed by the processor further comprise milling the virtual restoration.

Images